P

Pixel

pixel-cli/pixel · unreleased source · 6c1d78d · Development & Workflow

by Pixel-CLIScan grade: caution

Local, deterministic code index that Claude Code, Codex, Pi, OpenCode and other coding agents query for signatures, callers, impact and Git history instead of reading whole files

InstallSourceClaim this plugin
Follow0
Trust Score59Security scan59Components15
Protect this install with HOL Guard

Guard checks the skills and MCP servers a plugin adds on your machine and asks you before a risky action runs. The scores above are free, and no plan changes them.

Is Pixel a fit?

From the plugin's manifest and HOL's scan. Anything the plugin does not declare is shown as not declared.

Works with

  • Claude Code
  • OpenCode
  • 15 skills

Before you install

Sign-in
Not declared
Declared access
Not declared
License
Not declared

Check before relying on it

  • Some security checks did not finish: Cisco skill scan and HOL plugin scan. See the evidence
  • 3 medium findings from the scan. See the evidence
  • The publisher has not verified ownership on HOL.
  • No license declared in the manifest.

What is Pixel?

Pixel is a published development & workflow plugin for AI coding agents that works with Claude Code and OpenCode, developed by Pixel-CLI and distributed through the HOL AI plugin registry. Local, deterministic code index that Claude Code, Codex, Pi, OpenCode and other coding agents query for signatures, callers, impact and Git history instead of reading whole files.

Canonical slug
pixel-cli/pixel
Version
unreleased source · 6c1d78d · updated Oct 15, 2026

Registry snapshot

Owner verification
Not verified
Scanner
Registry fallback scan
Security result
Caution
Digest verified
Yes
15 bundled skillsRead, copy or download each SKILL.mdOpen skills

Trust and security

Trust & reputation

59

HOL Trust Score

Per-metric points (0–100 each) combined via a weighted average into the overall score.

Installability
64/100
Maintenance
30/100
MCP server setup
100/100
Plugin Security
59/100
Provenance
70/100
Publisher Quality
75/100

Provenance

Plugin root
.
Source repo
https://github.com/Pixel-CLI/pixel
Source commit
6c1d78d8700b…
Publisher verified
No
Owner verified
Not owner verified

Continuous scanner CI not detected

This plugin remains listed. Its overall trust score is reduced by 10% because security checks are not maintained in the source repository's CI.

Optional: maintain the scanner in the source repository's CI to receive the full trust score. Listing does not require that change.

README badge not detected

Plugin owners can add the HOL badge to the repository README from Guard Plugins. Distribution, not security evidence. It adds a 2% engagement adjustment to the overall trust score and never changes the security result.

Security posture

See how the Trust Score is computed
Caution
Security result
59
Security score
0
High findings
Provider
registry-broker-fallback
Grade
F · caution
Version
Unknown
cisco-skill-scanner: unknown

Published advisories

  • GHSA-c9f5-vxc4-wjphGitHub security advisoriesPublished

    Committed .pixel/ symlinks let a hostile repository make Pixel write, truncate or read files outside the repository

GitHub security advisories are those the source repository has published. Checked .

Findings

mediumpublishabilitypublishability.link.missing.websiteURL

websiteURL should be present for marketplace readiness.

mediumpublishabilitypublishability.link.missing.privacyPolicyURL

privacyPolicyURL should be present for marketplace readiness.

mediumpublishabilitypublishability.link.missing.termsOfServiceURL

termsOfServiceURL should be present for marketplace readiness.

lowoperational-securitysupply-chain.lockfile-missing

Repository snapshot does not include a lockfile.

infoskill-securityskill-scan.unavailable

Cisco skill scanner exited with code 1: Error loading skill: No SKILL.md and no .md files found in /tmp/hol-skill-safety-a0EWWK (lenient mode requires at least one markdown file)

infoskill-securityskill-scan.unavailable

Cisco skill scanner exited with code 1: Error loading skill: No SKILL.md and no .md files found in /tmp/hol-skill-safety-1AbQIP (lenient mode requires at least one markdown file)

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner exited with code 1: Error loading skill: No SKILL.md and no .md files found in /tmp/hol-skill-safety-7tAPuC (lenient mode requires at least one markdown file)

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner exited with code 1: Error loading skill: No SKILL.md and no .md files found in /tmp/hol-skill-safety-Tp3A26 (lenient mode requires at least one markdown file)

infoskill-securityskill-scan.unavailable

Cisco skill scanner exited with code 1: Error loading skill: No SKILL.md and no .md files found in /tmp/hol-skill-safety-eHtm4N (lenient mode requires at least one markdown file)

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner exited with code 1: Error loading skill: No SKILL.md and no .md files found in /tmp/hol-skill-safety-zdF97E (lenient mode requires at least one markdown file)

infoskill-securityskill-scan.unavailable

Cisco skill scanner exited with code 1: Error loading skill: No SKILL.md and no .md files found in /tmp/hol-skill-safety-ys9o7F (lenient mode requires at least one markdown file)

infoskill-securityskill-scan.unavailable

Cisco skill scanner exited with code 1: Error loading skill: No SKILL.md and no .md files found in /tmp/hol-skill-safety-vCEZL2 (lenient mode requires at least one markdown file)

Install guidance

Install in Source

Install from a native release archive or the assessed source revision.

Install guide
  1. 1

    Download the release archive

    Use a published GitHub release archive. The catalog version is the package version at the assessed commit.

    shell
  2. 2

    Or install the pinned Cargo source

    Pinned Git source. Check the publisher install guide before using a package registry.

    shell
  3. 3

    Follow the publisher install guide

    https://github.com/Pixel-CLI/pixel/blob/6c1d78d8700baf76a80dd05b2e6a2290aaca5098/docs/INSTALL.md

Did setup work in Source?

No setup reports for Source yet. Self-reported by signed-in visitors. Copying a command is not counted, and most installs are never reported.

Attested installs: Fewer than 10 attested installs of this plugin in week 2026-W43, so no number is shown. Counted from opt-in HOL Guard install reports, once per machine and runtime, and never mixed with the answers above. How install reports work.

Loading reviews

Plugin manifest

{
  "name": "pixel",
  "version": "0.0.0",
  "description": "Local, deterministic code index that Claude Code, Codex, Pi, OpenCode and other coding agents query for signatures, callers, impact and Git history instead of reading whole files",
  "repository": "https://github.com/Pixel-CLI/pixel",
  "homepage": "https://github.com/Pixel-CLI/pixel",
  "interface": {
    "displayName": "Pixel",
    "developerName": "Pixel-CLI",
    "category": "Development & Workflow"
  },
  "skills": "./",
  "holPackageManager": "cargo",
  "holManifestOrigin": "synthesized",
  "registryIndexVersion": 5
}

Skills

15 SKILL.md files ship with this plugin. Preview, copy, or download each one, then install them with the Skills CLI.

Share
skills-cli

  • agent-session-debugging

    .agents/skills/agent-session-debugging/SKILL.md

    Operate real pi, agy, Claude, and Codex sessions in Herdr to diagnose tool behavior from transcripts, ask a CLI directly when its own behavior is unclear, then implement, retest, and redeploy a verified fix.

    Raw SKILL.md

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

  • arena

    .agents/skills/arena/SKILL.md

    Run one of eight standard prompts in two Codex panes side by side in Herdr, one with Pixel's prompt-submit brief and one without, then compare tool calls, answers and wall time. One command runs, one aborts.

    Raw SKILL.md

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

  • docker-setup-smoke

    .agents/skills/docker-setup-smoke/SKILL.md

    Replay Pixel's new-user setup in Docker without an LLM — install through a release archive, install.sh, the Homebrew tap, or sources from main, a PR head or a pinned commit; then personal Claude/Codex/pi settings kept, idempotent reinstall, first pixel audit, doctor and --fix, project install, disabled classify and uninstall; with --agents, Claude Code, Codex and pi sessions against a scripted fake model show whether each receives the Pixel prompt, runs pixel and routes grep. Use for Linux setup smoke checks, not macOS behavior or real model inference.

    Raw SKILL.md

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

  • extract-probes

    .agents/skills/extract-probes/SKILL.md

    Mine this project's local agent transcripts for the tool sequences a brief probe could replace: /extract-probes, 'mine transcripts for probes', 'which tool sequences could the brief replace'. Ranks the most common pre-answer call sequences by question kind and maps each to an existing probe or a candidate.

    Raw SKILL.md

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

  • improve-codebase-architecture

    .agents/skills/improve-codebase-architecture/SKILL.md

    Find deepening opportunities in pixel's crates (shallow modules to merge behind a smaller interface, leaking seams, logic only testable past its interface), scouted with pixel's own churn, size, caller and area data, presented as a local HTML report of before/after cards with their real cost (diff size, mutants, ARCHITECTURE.md sections, PR stack), then grilled through the candidate the user picks until it becomes a task on project 3. Adapted from Matt Pocock's improve-codebase-architecture skill. Manual only: "/improve-codebase-architecture [area]", "revue d'archi", "où approfondir les modules".

    Raw SKILL.md

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

  • pixel-retro

    .agents/skills/pixel-retro/SKILL.md

    Mine the last 24 h (or a given window) of pixel usage — every repo's `.pixel/actions.jsonl` plus the agent transcripts indexed by `pixel recall` (claude, codex, pi…) — for frictions pixel actually caused, verify each one against the current binary and code, and propose ranked, evidence-backed improvements (bug fix, error message, flag, agent prompt, rule, doc); for the pixel repo itself, also measure each pull request from first edit to validated CI and where agents sat idle (`lead_time.py`). Suggests only; implements nothing without the user's pick. Use when the user says "/pixel-retro", "retro pixel", "qu'est-ce qui a coincé avec pixel", "améliorations pixel depuis les transcripts", "pixel friction", "où l'agent attend", "bottleneck", "lead time", or asks what to improve in pixel or its development workflow from recent sessions.

    Raw SKILL.md

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

  • pr

    .agents/skills/pr/SKILL.md

    Write or revise a pixel pull request body: fill .github/pull_request_template.md (Closes #N, Summary with a call-tree, file-tree or pseudocode sketch built from pixel's own graph, before/after Evidence with commands, Merge Danger as door and blast radius, Docs touched). Use when opening a PR, rewriting its description, or answering a reviewer who asks what a PR does or risks. Adapted from Matt Pocock's MIT pr skill and HumanLayer's MIT show-me skill (UPSTREAM pins both).

    Raw SKILL.md

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

  • probe

    .agents/skills/probe/SKILL.md

    Create or refine a brief probe, make a question zero-call, or run /probe \"<question>\" [--repo path]: run the question with the current Pixel brief, stop if it is already zero-call, otherwise translate the calls the agent still made into evidence, write a generic probes/<name>/ script, prove it offline and live, and hand back a report and a commit.

    Raw SKILL.md

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

  • release

    .agents/skills/release/SKILL.md

    Cut a pixel release end to end — pick the version, prepare the release commit (changelog cut, lockstep version bump, Cargo.lock, check-release) with prepare.sh in a pull request into main, tag vX.Y.Z on its merge to trigger .github/workflows/release.yml, and verify the published release, the install.sh asset and the Homebrew tap with evidence. Also covers resuming an interrupted release, patch releases while main is not releasable, and recovering from a failed Release run. Use when asked to release, publish, tag or ship a new pixel version, bump the version, cut the changelog, check a published release, or when the Release workflow failed.

    Raw SKILL.md

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

  • rust-guidelines

    .agents/skills/rust-guidelines/SKILL.md

    Microsoft's Pragmatic Rust Guidelines (M-* rules) applied to new or changed Rust code in this workspace. Use whenever writing, refactoring or reviewing code under crates/ — API shape, error types, panics vs errors, docs, performance, test design. Adds the borrowing, type-state, TODO and test-naming rules from Apollo GraphQL's rust-best-practices that Microsoft does not cover. Complements .agents/rules (mutation gate, lint idioms), does not replace them.

    Raw SKILL.md

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

  • section-redesign

    .agents/skills/section-redesign/SKILL.md

    Redesign one or two sections of the pixel-cli.dev home (website/layouts/index.html) with the loop the hero went through for task #401 — critique as a visitor, an artifact of 2–3 mocked variants with votable points, the user's vote, synthesis iterations, every claim checked against the code and the benchmarks, then the Hugo implementation with desktop and mobile captures. Use when the user says "/section-redesign", "on itère sur la section …", "refais la section #problem", "même méthode que le hero", or names a home section (#problem, #scope, #toolbox, #how, #agents, #faq, #install and its #your-number checks; the page has no closing chapter) to rework.

    Raw SKILL.md

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

  • validation-loop

    .agents/skills/validation-loop/SKILL.md

    Publish Pixel PRs promptly with optional local diagnosis and required CI validation.

    Raw SKILL.md

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

  • pixel-call-path

    eval/arena/skills/pixel-call-path/SKILL.md

    Trace a named code entry to a named destination when the request asks how execution reaches that point; exclude generic explanations, text searches, and edits.

    Raw SKILL.md

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

  • pixel-question-evidence-filtered

    eval/arena/skills/pixel-question-evidence-filtered/SKILL.md

    Use Pixel for bounded evidence when a code question asks for an exact symbol definition or export, or the files affected by a rename. Do not use for unrelated questions.

    Raw SKILL.md

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

  • pixel-question-evidence

    eval/arena/skills/pixel-question-evidence/SKILL.md

    Use Pixel for bounded evidence when a code question asks for an exact symbol definition or export, or the files affected by a rename. Do not use for unrelated questions.

    Raw SKILL.md

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

File inventory

.agents/skills/agent-session-debugging/SKILL.md

skill

10,313 bytes

1619faab797b9cc1…

.agents/skills/arena/arena.sh

file

56,330 bytes

f7933bf39eb4e2f9…

.agents/skills/arena/hook-wrap.py

file

5,262 bytes

2b1ff8894a20c058…

.agents/skills/arena/session-digest.py

file

4,750 bytes

3172e39b53af56e4…

.agents/skills/arena/SKILL.md

skill

12,972 bytes

098b44a4f6cfe1cb…

.agents/skills/docker-setup-smoke/scripts/agents.sh

file

7,751 bytes

048c34120b0a78ef…

.agents/skills/docker-setup-smoke/scripts/bootstrap.sh

file

1,063 bytes

8b069ccfd8baf480…

.agents/skills/docker-setup-smoke/scripts/brew.sh

file

2,654 bytes

55735ac9d0307e16…

.agents/skills/docker-setup-smoke/scripts/checks.sh

file

12,074 bytes

6cc3475647e50c7c…

.agents/skills/docker-setup-smoke/scripts/fake-llm.py

file

9,059 bytes

2ca707c422f27278…

.agents/skills/docker-setup-smoke/scripts/installer.sh

file

934 bytes

3279d3aeaebf20eb…

.agents/skills/docker-setup-smoke/scripts/run.sh

file

5,705 bytes

26660c72887e7a66…

.agents/skills/docker-setup-smoke/scripts/source.sh

file

1,051 bytes

d26fc89f7b5d8eea…

.agents/skills/docker-setup-smoke/scripts/test-runner.py

file

11,383 bytes

e7ad449338a0bde3…

.agents/skills/docker-setup-smoke/SKILL.md

skill

10,941 bytes

42ec49661e1752a0…

.agents/skills/extract-probes/SKILL.md

skill

3,153 bytes

660eeb2ae1a789df…

.agents/skills/improve-codebase-architecture/agents/openai.yaml

file

166 bytes

c8cb20f68ebf0edb…

.agents/skills/improve-codebase-architecture/DESIGN.md

file

6,899 bytes

99d13bfa310038ab…

.agents/skills/improve-codebase-architecture/HTML-REPORT.md

file

4,483 bytes

38ba1f3102d0bedf…

.agents/skills/improve-codebase-architecture/SKILL.md

skill

9,287 bytes

cd6ffb5cc020f715…

.agents/skills/pixel-retro/adherence.py

file

18,708 bytes

7c0b0a597f38f725…

.agents/skills/pixel-retro/lead_time.py

file

12,877 bytes

e05ce804308d18b8…

.agents/skills/pixel-retro/ledger.py

file

1,586 bytes

08eaf4ed55dce4e6…

.agents/skills/pixel-retro/roots.py

file

3,261 bytes

c1e77a15feeb8871…

.agents/skills/pixel-retro/SKILL.md

skill

20,866 bytes

b8362bf93529b83f…

.agents/skills/pixel-retro/slow.py

file

4,691 bytes

d777b0be50cdf026…

.agents/skills/pixel-retro/test_adherence.py

file

9,881 bytes

b9d22b9be9581d1c…

.agents/skills/pixel-retro/test_lead_time.py

file

6,978 bytes

f7756d56a8702b98…

.agents/skills/pr/SKILL.md

skill

5,293 bytes

b73c2bcaba55f947…

.agents/skills/probe/SKILL.md

skill

7,847 bytes

a0a330bb188f7a54…

.agents/skills/release/check-candidate.py

file

3,318 bytes

9a2f56ac3f9bc081…

.agents/skills/release/prepare.sh

file

22,824 bytes

bc88c4ee59b7136a…

.agents/skills/release/references/security-release.md

file

3,654 bytes

ef2b2bc15be0b835…

.agents/skills/release/SKILL.md

skill

30,810 bytes

d64bd49484aa51e2…

.agents/skills/rust-guidelines/guidelines.txt

file

135,404 bytes

c9f1ac1c9d52a65e…

.agents/skills/rust-guidelines/SKILL.md

skill

10,086 bytes

f87c30ea64919c9e…

.agents/skills/section-redesign/assets/review-sheet.html

file

10,346 bytes

6359c8779c9a2ffd…

.agents/skills/section-redesign/SKILL.md

skill

8,672 bytes

58b8e2afae11a99e…

.agents/skills/validation-loop/SKILL.md

skill

1,565 bytes

3b0cb36bfc54b43e…

.codex-plugin/plugin.json

plugin-manifest

528 bytes

5c8471e10523d625…

AGENTS.md

file

17,510 bytes

05d3fa4fba70e4d5…

Cargo.lock

file

106,141 bytes

8697a0ceed53099c…

Cargo.toml

file

5,274 bytes

1c4c8653852811c5…

eval/arena/skills/pixel-call-path/agents/openai.yaml

file

154 bytes

74c8efd8e7debe7b…

eval/arena/skills/pixel-call-path/SKILL.md

skill

1,202 bytes

05f90db8edba5980…

eval/arena/skills/pixel-question-evidence-filtered/agents/openai.yaml

file

166 bytes

3d77276b34637cc9…

eval/arena/skills/pixel-question-evidence-filtered/SKILL.md

skill

1,684 bytes

e372258779a6f1cf…

eval/arena/skills/pixel-question-evidence/agents/openai.yaml

file

155 bytes

4bc31ab105672a6e…

eval/arena/skills/pixel-question-evidence/SKILL.md

skill

1,613 bytes

4054ca19fa6eacc1…

README.md

file

7,465 bytes

43dc2bd277aeeb08…

README.md

file

7,465 bytes

43dc2bd277aeeb08…

Pixel — Frequently asked questions

What is Pixel?
Pixel is an AI plugin in the HOL registry. Local, deterministic code index that Claude Code, Codex, Pi, OpenCode and other coding agents query for signatures, callers, impact and Git history instead of reading whole files.
How do I install Pixel?
Install Pixel in your harness: Source — https://github.com/Pixel-CLI/pixel/releases; OpenCode — npx [email protected] add Pixel-CLI/pixel; Any agent — npx [email protected] add Pixel-CLI/pixel. Full step-by-step guidance is on the HOL plugin page.
How do I install Pixel in Source?
To install Pixel in Source, start with https://github.com/Pixel-CLI/pixel/releases. The complete step-by-step install guide for Source is on the HOL plugin page.
How do I install Pixel in OpenCode?
To install Pixel in OpenCode, start with npx [email protected] add Pixel-CLI/pixel. The complete step-by-step install guide for OpenCode is on the HOL plugin page.
How is the Trust Score for Pixel computed?
Pixel has a HOL Trust Score of 59 out of 100. The score is a weighted sum of six components from a static scan of the source, capped for high-severity findings and adjusted by two disclosed policies. Memberships and payments are not inputs, and a scan is not a safety guarantee. Full breakdown: https://hol.org/registry/plugins/pixel-cli%2Fpixel/trust
Who publishes Pixel?
Pixel is published by Pixel-CLI and listed on HOL.

Directory acceptance

Listed in 0 of 5 directory lists

Read from the list each directory publishes on GitHub. Being listed means the directory accepted the plugin; it is not a HOL security rating.

Lists last read . HOL re-reads them every day.

Submitting it? Check it against each directory's rules

Install signal

HOL cannot see every install. These are separate signals from different sources, so they are not added together. Counts under each floor show as <N.

Install commands issued here
<5
HOL Guard install commands issued from this listing, last 28 days.
Opt-in install reports
<10
Machines that reported installing it through HOL Guard in week 2026-W43. Reporting is opt-in, so most installs are not counted.
HOL Guard workspaces
<5
Workspaces that approved it or include it in an approved-plugin feed, as of today.

Related plugins

Ordered by Trust Score. Listings cannot pay for these positions. Check each one fits your task before switching from Pixel.

Alternatives in Development & Workflow

See all Development & Workflow plugins

Reviews and similar plugins