New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Validate Agent Work

by kryptamine in kryptamine/herdr-auto-title

Final checklist before handing work back in the herdr-auto-title repo: review the diff, run make check, apply the comment and AGENTS.md rules, then report.

MITAuto-check passedDevelopment

Install Validate Agent Work

skills CLI
$ npx skills add kryptamine/herdr-auto-title --skill validate-agent-work -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install kryptamine/herdr-auto-title validate-agent-work --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/kryptamine/herdr-auto-title.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/validate-agent-work .claude/skills/validate-agent-work && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
validate-agent-work
GitHub stars
237
Token cost
~605 tokens
SKILL.md length
296 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Final checklist before handing work back in the herdr-auto-title repo: review the diff, run make check, apply the comment and AGENTS.md rules, then report.

  • Works in 7 steps: See what changed — the branch against… → Run the gate → Comment pass — the ## Comment pass in → …
  • Finishing any change to the herdr-auto-title repository
  • Calls make and git
  • Checking work before handing it back after adding a feature or fixing a bug

What it does

This is a project-specific routine for finishing a change. The agent first lists what changed against `main` and in the working tree without staging anything, then runs `make check`, whose formatting step rewrites files, so a file is re-read before it is edited again. A comment pass over the comments the change added or touched follows, using the repo's comments rule file.

Next the diff is read against the mandatory rules in AGENTS.md, which the linter does not enforce. Two of them need a search: fields, methods or constants added with no reader in the same change, and probes whose findings never reached the Herdr socket API doc. `make ps` confirms nothing was left running. Failures are fixed and the step is re-run, or reported if they are not the agent's to fix, and the final report is a short confirmation, a one-line list of fixes or a note on what is still broken. CI also builds on the minimum Go version in go.mod and on macOS.

When your agent uses it

  • Finishing any change to the herdr-auto-title repository
  • Checking work before handing it back after adding a feature or fixing a bug
  • Reviewing Go, Python or documentation edits against the repo's AGENTS.md rules

Example prompts

  • “Validate my changes before I hand this back.”
  • “Run the checks on this branch and fix whatever the linter finds.”
  • “Check my work against AGENTS.md and tell me if anything is still left running.”

Requirements

  • make, to run the repository's check target

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. See what changed — the branch against main, and whatever is not
  2. Run the gate
  3. Comment pass — the ## Comment pass in
  4. Read the diff against the mandatory rules in AGENTS.md — the language,
  5. Check nothing was left running
  6. Fix and re-run — fix what a step found, then run that step again to
  7. Report — always say what happened

What it can do on your machine

Read from SKILL.md and the folder at commit 0cf776d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • make
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Validate Agent Work loads about 605 tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 296 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~65
When it runs · the whole SKILL.md, loaded when a task matches
~605

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from kryptamine/herdr-auto-title at commit 0cf776d, republished under its MIT licence (© kryptamine). 296 words, ~605 tokens.

Download SKILL.mdSave it as .claude/skills/validate-agent-work/SKILL.md (or your agent's skills folder).
name
validate-agent-work
description
Use when finishing any change to this repository, or when the user says "validate", "check my work", "run checks", or "verify changes". Also use automatically after adding a feature, fixing a bug, or editing Go, Python or documentation here.

Validate Agent Work

The rules live in AGENTS.md and CONTRIBUTING.md; this is the order to check them in before handing work back.

Steps

  1. See what changed — the branch against main, and whatever is not committed yet:

    bash
    git diff --name-only main...HEAD
git status --short

    Stage nothing: every check below runs over the whole module, and the index is the user's to decide.

  2. Run the gate:

    bash
    make check

    fmt runs first and rewrites files, so re-read one before editing it again.

  3. Comment pass — the ## Comment pass in .claude/rules/comments.md, over the comments this change added or touched.

  4. Read the diff against the mandatory rules in AGENTS.md — the language, commit, type, script and comment rules, and the "Working here" list. The linter checks none of them. Two need a search rather than a read: a field, method or constant added without a reader in the same change, and a probe whose finding has not reached docs/architecture/herdr-socket-api.md, which is the record — AGENTS.md takes it only if it misleads the code in silence.

  5. Check nothing was left running:

    bash
    make ps

  6. Fix and re-run — fix what a step found, then run that step again to confirm it. If a failure is not yours to fix, say so rather than working around it.

  7. Report — always say what happened:

    • Clean: a brief confirmation.

    • Found and fixed, one line each:

      Validation found and fixed 3 issues:
- golangci-lint: unused parameter in resolver.qualify
- Comments: dropped a caller note in app/reads.go
- Type rule: removed PaneInfo.Cols, which nothing read

    • Still broken: what is wrong and why you could not fix it.

make check is the whole gate on this machine, but CI also builds and tests on the Go floor go.mod names and on macOS — see CONTRIBUTING's "Pull requests". The user should never be surprised by a failure that could have been caught here.

© kryptamine, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/validate-agent-work of kryptamine/herdr-auto-title.

Open the folder on GitHubat commit 0cf776d

Compare with similar skills

Validate Agent Work next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Validate Agent Work compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Validate Agent Work this skillkryptamine/herdr-auto-title237—~605Automated safety check: PassMIT
Saleor Commit Workflowsaleor/saleor23k—~575Automated safety check: PassBSD-3-Clause
Qt6 QML Code Reviewerx-tools-author/x-tools1.1k1 repos~3.6kAutomated safety check: PassBSD-3-Clause
Adk Setupgoogle/adk-python22k—~993Automated safety check: NotesApache-2.0
Python Devdatabricks-solutions/ai-dev-kit1.9k—~1.6kAutomated safety check: PassCustom licence
Windows Path Rename981377660LMT/algorithm-study278—~540Automated safety check: PassNone

Similar skills

  • Saleor Commit Workflow

    saleor/saleor

    Commits changes in the Saleor codebase and works through pre-commit hook failures from ruff, mypy, the GraphQL schema check and the migrations check.

    23k GitHub stars~575 tokensUpdated today
    DevelopmentAuto-check passed

  • Qt6 QML Code Reviewer

    x-tools-author/x-tools

    Runs a 47-rule deterministic QML linter, then six parallel deep-analysis passes over bindings, layout, loaders, delegates, states, and performance.

    1.1k GitHub starsUsed in 1 repo~3.6k tokens
    DevelopmentAuto-check passed

  • Adk Setup

    google/adk-python

    Official

    Sets up a local ADK Python development environment in a git clone of the open-source adk-python repository: a uv virtual environment, all dependency extras, pre-commit hooks, and a first unit-test…

    22k GitHub stars~993 tokensUpdated today
    DevelopmentAuto-check: notes

  • Python Dev

    databricks-solutions/ai-dev-kit

    Python development guidance with code quality standards, error handling, testing practices, and environment management.

    1.9k GitHub stars~1.6k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

  • Windows Path Rename

    981377660LMT/algorithm-study

    Sanitize Git paths that are invalid on Windows (for example :, ", |, ?, and trailing dot/space) and commit safe renames.

    278 GitHub stars~540 tokensUpdated 3 mo ago
    DevelopmentAuto-check passed

  • WebRTC Include Cleaner

    webrtc-sdk/webrtc

    Runs the WebRTC include-cleaner tool to add missing and remove unused C++ include directives before uploading a CL or after refactoring.

    446 GitHub starsUsed in 1 repo~545 tokens
    DevelopmentAuto-check passed

Works with

Categories

Questions about Validate Agent Work

What does Validate Agent Work do?

Final checklist before handing work back in the herdr-auto-title repo: review the diff, run make check, apply the comment and AGENTS.md rules, then report. This is a project-specific routine for finishing a change. The agent first lists what changed against `main` and in the working tree without staging anything, then runs `make check`, whose formatting step rewrites files, so a file is re-read before it is edited again.

When should I use Validate Agent Work?

Validate Agent Work fits situations like: finishing any change to the herdr-auto-title repository; checking work before handing it back after adding a feature or fixing a bug; reviewing Go, Python or documentation edits against the repo's AGENTS.md rules.

How do I install Validate Agent Work in Claude Code?

Run `npx skills add kryptamine/herdr-auto-title --skill validate-agent-work -a claude-code`. Or copy the skill folder (.claude/skills/validate-agent-work in kryptamine/herdr-auto-title) into .claude/skills/validate-agent-work in your project. Claude Code loads it when a task matches its description.

How do I install Validate Agent Work in Codex?

Run `npx skills add kryptamine/herdr-auto-title --skill validate-agent-work -a codex`. Or copy the skill folder (.claude/skills/validate-agent-work in kryptamine/herdr-auto-title) into .agents/skills/validate-agent-work in your project. Codex loads it when a task matches its description.

Can I use Validate Agent Work in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add kryptamine/herdr-auto-title --skill validate-agent-work -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/validate-agent-work, .gemini/skills/validate-agent-work, .github/skills/validate-agent-work and .opencode/skills/validate-agent-work in your project.

What does Validate Agent Work need to run?

Going by SKILL.md and its folder, Validate Agent Work needs the command-line tools its instructions call (make and git). Our summary lists: make, to run the repository's check target.

Does Validate Agent Work access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Validate Agent Work safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Validate Agent Work use?

Validate Agent Work is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Validate Agent Work use?

About 605 tokens (SKILL.md is roughly 2.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Validate Agent Work?

Skills that share tags, products or a category with Validate Agent Work: Saleor Commit Workflow (saleor/saleor, 23k stars), Qt6 QML Code Reviewer (x-tools-author/x-tools, 1.1k stars), Adk Setup (google/adk-python, 22k stars) and Python Dev (databricks-solutions/ai-dev-kit, 1.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Validate Agent Work?

kryptamine (a GitHub user) maintains it in kryptamine/herdr-auto-title, which has 237 GitHub stars. The repository was last updated on October 6, 2026.

Source: kryptamine/herdr-auto-title on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.