Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/coralogix/canopyWrote 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/commands/coralogix/canopy/pre-release-audit)<a href="https://agentmods.dev/commands/coralogix/canopy/pre-release-audit"><img src="https://agentmods.dev/badge/commands/coralogix/canopy/pre-release-audit.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00521 |
| Opus 5 | $0.00000 | $0.00260 |
| Sonnet 5 | $0.00000 | $0.00104 |
| Haiku 4.5 | $0.00000 | $0.00052 |
Grade A, and why
pre-release-audit 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 8d 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.
What it actually says
/pre-release-audit
Run a pre-release checklist and report what's ready, what's not, and what needs attention.
Steps
- Uncommitted changes — Run
git status. Flag any modified or untracked files. - Current branch — Run
git branch --show-current. Warn if not on the expected release branch. - Version consistency — Find all version references:
pyproject.toml(Python:version = "...")package.json(Node:"version": "...")Cargo.toml(Rust:version = "...")CHANGELOG.md(most recent entry version)- Any other manifest files Compare them. Flag any mismatch.
- Tests — Check if a test suite exists. If
pyproject.tomlis present: notecd cli && uv run pyteststatus (run if possible). Same forpackage.json→npm test. - Lint — Check for lint config (
.ruff.toml,.eslintrc, etc.). Note the lint command and run if possible. - CHANGELOG.md — Check that it exists and has an entry for the current version (not just
[Unreleased]). - Open items — Look for
TODO,FIXME,HACKin recently changed files (git diff HEAD~5..HEAD). Flag any that seem release-blocking. - Dependencies — If a lock file exists (
uv.lock,package-lock.json,Cargo.lock), check that it's committed.
Output Format
## Pre-Release Audit
### ✅ Ready
- [item]: [detail]
### ❌ Blocking
- [item]: [what's wrong and where to fix it]
### ⚠️ Needs Attention
- [item]: [what to check]
### ⬜ Could Not Check
- [item]: [why — missing credentials, tool not available, etc.]
---
**Summary:** X of Y checks passing. [Release-ready | Not ready — see blocking items above]
Rules
- Be specific: file paths, line numbers, exact version strings
- Only mark something ❌ Blocking if it would likely cause a production issue
- Don't fail a release for stylistic preferences — focus on correctness
- If you can't run a check (no permission, missing tool), put it in ⬜ rather than guessing
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.
- 8d ago First seen · 49 lines · 0 tokens per session scan A 13afb45620b5
pre-release-audit is a command published in the GitHub repository coralogix/canopy (89 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 521 tokens. 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 2026-08-30.
Other commands, from other repositories
land
Cadence-tick autonomous PR babysitter (CI-fix, resolve, converge, merge, close, release).
release-notes
Generate consistent, well-structured release notes from git history. Triggered on release tags following semver patterns (v..) to produce categorized changelog with breaking changes, features, fixes, and contributor attribution.
ship
Ship is the operational release-prep flow for a connected project repo.
release-plan
A release-planning command for a software change. It documents the release scope, rollback plan, gradual or full rollout, and monitoring before waiting for human approval.
release
Standalone SDK release command for the BUILD repo. Not a workspace phase — runs independently after any number of implement/redteam cycles. Handles PyPI publishing, documentation deployment, and CI management for the kailash Python SDK and its framework packages.
create-pr
Push the current branch and open a pull request into main with a structured description derived from the branch's commits and issue references.