Borrowing it
Nothing to install: this file belongs to sagar-shirwalkar/collibra-atlas. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sagar-shirwalkar/collibra-atlas/main/.agents/skills/skill-compliance/SKILL.mdgit clone --depth 1 https://github.com/sagar-shirwalkar/collibra-atlasWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sagar-shirwalkar/collibra-atlas/skill-compliance)<a href="https://agentmods.dev/skills/sagar-shirwalkar/collibra-atlas/skill-compliance"><img src="https://agentmods.dev/badge/skills/sagar-shirwalkar/collibra-atlas/skill-compliance/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sagar-shirwalkar/collibra-atlas/skill-compliance"><img src="https://agentmods.dev/badge/skills/sagar-shirwalkar/collibra-atlas/skill-compliance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00062 | $0.00992 |
| Opus 5 | $0.00031 | $0.00496 |
| Sonnet 5 | $0.00012 | $0.00198 |
| Haiku 4.5 | $0.00006 | $0.00099 |
Grade A, and why
skill-compliance scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit the project's skills against a set of compliance checks. Each check is a standalone Python script in scripts/ that follows a plugin pattern.
Leading words
- Audit — A scripted compliance check with a binary outcome (pass/fail) and evidence. Each audit is independent, composable, and cacheable.
- Plugin — A script in
scripts/that can be dropped in or removed without changing anything else. Adding a new check means adding one file and one entry inreferences/checks.md. - Staleness — The risk that cached results no longer reflect reality. Managed by per-check TTLs and the agent always printing results after running.
Branches
audit-all
Run every check in order, reading from cache for non-stale checks.
Completion criterion: every check has a pass/fail result and the summary has been printed to chat.
-
Resolve paths. Determine the skills directory (
.agents/skills/), the cache file (assets/cache.json), and the project root. -
Read cache. Load
assets/cache.json. If it doesn't exist or is empty, start fresh. -
Determine stale checks. For each check in the registry (
references/checks.md), compare the cached timestamp against the check's TTL. A check is stale if:- It has no cache entry, OR
now - cached_timestamp > ttl
-
Run stale checks. For each stale check, execute its script:
python scripts/check_<name>.py \ --skills-dir <path> \ --cache <cache_path> \ --update-cacheThe script writes its result into the cache and returns JSON to stdout.
-
Print summary. After all checks complete, print a concise summary to the chat with one line per check:
✓ handoff-compliance — agent-handoff exists, AGENTS.md has protocol + compaction ✗ structure — untracked skill: skill-compliance not in AGENTS.md catalog ✓ invocation — all frontmatter/AGENTS.md consistent ...Lead with failures (✗) so the user sees problems first.
-
Offer to fix. For any failing check, ask if the user wants automatic remediation before ending.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/cache.json 3 B
- references/checks.md 1.4 KB
- scripts/check_completion_criteria.py 3.9 KB runs code
- scripts/check_description.py 4.9 KB runs code
- scripts/check_handoff_compliance.py 4.2 KB runs code
- scripts/check_invocation.py 4.4 KB runs code
- scripts/check_leading_words.py 4.7 KB runs code
- scripts/check_structure.py 5.0 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 96 lines · 62 tokens per session scan A f424a16cb9cc
skill-compliance is a skill published in the GitHub repository sagar-shirwalkar/collibra-atlas (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 62 tokens to every session and 992 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…