release-check

release-check is a skill for Claude Code from ArtemioPadilla/agent-triforce. It costs 44 tokens per session (2,009 once invoked), scanned A, original, MIT.

A pre-release checklist that checks whether a software version is ready to ship. It reviews tests, security findings, changelog entries, dependencies, and technical debt, then reports GO or NO-GO.

In plain words
What is it for?
Use it to verify test coverage, open high-severity security issues, changelog completeness, dependency freshness, and technical debt before publishing a version.
Why use it?
It brings release risks into one structured report instead of making you check separate files and tools by hand. It also points out what needs fixing before release.

Skill for Claude Code

Written for Claude Code: context: fork in frontmatter. Also seen: agent in frontmatter.

Good fit Use it to verify test coverage, open high-severity security issues, changelog completeness, dependency freshness, and technical debt before publishing a version.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/artemiopadilla/agent-triforce/release-check
Install

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.

Any agent
npx skills add ArtemioPadilla/agent-triforce --skill release-check
Clone the repo
git clone --depth 1 https://github.com/ArtemioPadilla/agent-triforce

Made for: Claude Code.

Wrote 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.

agentmods badge for release-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/artemiopadilla/agent-triforce/release-check/github.svg)](https://agentmods.dev/skills/artemiopadilla/agent-triforce/release-check)
Your own site
<a href="https://agentmods.dev/skills/artemiopadilla/agent-triforce/release-check"><img src="https://agentmods.dev/badge/skills/artemiopadilla/agent-triforce/release-check/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.

agentmods 80×15 button for release-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/artemiopadilla/agent-triforce/release-check"><img src="https://agentmods.dev/badge/skills/artemiopadilla/agent-triforce/release-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,009 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.02009
Opus 5 $0.00022 $0.01005
Sonnet 5 $0.00009 $0.00402
Haiku 4.5 $0.00004 $0.00201

Measured 11d ago against content hash e182e815d662, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

release-check 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.

.claude/skills/release-check/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run a pre-release verification for: $ARGUMENTS

This is the highest-stakes checklist in the system. Like a pilot's pre-flight check, every item matters.

Follow these steps:

SIGN IN:

  • Run the SIGN IN checklist from your agent file
  • Note any known risks or concerns about this release
  • Determine the version being checked (from $ARGUMENTS, CHANGELOG.md, or package manifest)

RELEASE CRITERIA EVALUATION:

Evaluate each of the following 8 criteria. For each one, record: status (PASS/FAIL/N/A), actual value, threshold, and remediation steps if failing.

Criterion 1 -- Test Coverage (threshold: 80%)

  1. Check for coverage reports: look for coverage/, htmlcov/, .coverage, coverage.xml, or lcov.info
  2. If a coverage report exists, extract the overall coverage percentage
  3. If no coverage report exists, check if a test runner is configured (pytest, vitest, jest) and note that coverage was not measured
  4. Record: actual coverage % (or "not measured"), PASS if >= 80%, FAIL otherwise

Criterion 2 -- Security Scanner Status (threshold: 0 open Critical/High) 5. Read docs/reviews/security-audit-trail.md if it exists 6. Count open (unresolved) findings with Critical or High severity 7. Also check the most recent security audit in docs/reviews/security-audit-*.md 8. Record: count of open Critical/High findings, PASS if 0, FAIL otherwise 9. For each open finding, note its ID and a one-line summary as remediation

Criterion 3 -- CHANGELOG Completeness (threshold: entry exists for current version) 10. Read CHANGELOG.md 11. Check that an entry exists under ## [Unreleased] or ## [{version}] with at least one item 12. Record: PASS if entry exists with content, FAIL if empty or missing

Criterion 4 -- Dependency Freshness (threshold: 0 known Critical CVEs) 13. Check for dependency manifests: requirements.txt, package.json, Cargo.toml, go.mod 14. If npm audit, pip-audit, or equivalent is available, run it and check for Critical CVEs 15. If no audit tool is available, note as "not auditable" and record as PASS with caveat 16. Record: count of Critical CVEs found, PASS if 0, FAIL otherwise

Criterion 5 -- Tech Debt Severity (threshold: 0 P0/P1 items) 17. Read TECH_DEBT.md 18. Count active debt items with severity "Critical" (P0) or "High" (P1) 19. Record: count of P0/P1 items, PASS if 0, FAIL otherwise 20. For each P0/P1 item, note its ID and title as remediation

Quality Metrics (GQM -- Basili & Rombach 1988)

Every metric below traces to a business goal through a question. No measurement for measurement's sake.

Criterion 6 -- Phase Containment Effectiveness (PCE) (threshold: >= 70%)

  • Goal: Catch defects before release
  • Question: What % of defects were found in-phase (by Centinela during review) vs escaped (post-merge)?
  • Metric: PCE = (in-phase defects / total defects) * 100
  • Data source: Review reports in docs/reviews/ with finding status fields. In-phase = status reached Verified/Closed. Escaped = defects found after merge without prior review finding.
  • First run: If no review data exists, report "N/A -- baseline" (does not fail the gate)

Criterion 7 -- Defect Closure Rate (threshold: >= 90% Critical+Major closed)

  • Goal: Resolve defects promptly
  • Question: Are findings from reviews being closed before release?
  • Metric: (Critical+Major findings with status Closed or Verified) / (total Critical+Major findings) * 100
  • Data source: All review reports for the current release cycle
  • First run: "N/A -- baseline"

Criterion 8 -- Open Findings Trend (threshold: non-increasing)

  • Goal: Maintain stable codebase
  • Question: Is the defect arrival rate trending down?
  • Metric: Compare current open findings count to count at previous release-check
  • Data source: Previous release-check report in docs/reviews/
  • First run: "N/A -- baseline"

References: Basili & Rombach (1988), O'Regan (2019) Ch. 9.2 (GQM), Ch. 9.3.3 (PCE)

TIME OUT 1 -- Documentation & Debt Check (READ-DO): 21. Read CHANGELOG.md -- is it up to date with all changes? 22. Read TECH_DEBT.md -- are there any critical items blocking release? 23. Verify all specs in docs/specs/ with status "In Development" have acceptance criteria met 24. Verify documentation is current (README, API docs, ADRs)

Read the full file on GitHub · 159 lines

Changes

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.

  1. 11d ago First seen · 159 lines · 44 tokens per session scan A e182e815d662

Subscribe to this mod's changes

release-check is a skill published in the GitHub repository ArtemioPadilla/agent-triforce (3 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 2,009 once invoked, about $0.0002 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.