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.
npx agentmods add skills/d4rkninja/arcforge/quality-releasenpx skills add d4rkNinja/arcforge --skill quality-releasegit clone --depth 1 https://github.com/d4rkNinja/arcforgeWrote 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/d4rkninja/arcforge/quality-release)<a href="https://agentmods.dev/skills/d4rkninja/arcforge/quality-release"><img src="https://agentmods.dev/badge/skills/d4rkninja/arcforge/quality-release.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 | $0.00103 | $0.03713 |
| Opus 5 | $0.00051 | $0.01857 |
| Sonnet 5 | $0.00021 | $0.00743 |
| Haiku 4.5 | $0.00010 | $0.00371 |
Grade A, and why
quality-release 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 today.
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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Think Through Quality & Release Readiness
Overview
Production guidance for verification. Each reference paper captures the gap between "tests pass" and "production-safe": races that only appear under real isolation, failures that only appear when dependencies die, load targets with no workload model, and releases that never walked the cross-cutting checklist.
Core principle: Evidence, not assertion. Every quality or performance claim needs a test, measurement, or drill that would have failed if the claim were false — including the failure paths users and operators will actually hit. A plan is not executed evidence, and a waiver does not change what the evidence says.
Domain Law
NO 'DONE' CLAIM WITHOUT:
1. the minimum required primary paper(s) for the verification type selected from the context table;
2. a named workload, failure, or interleaving the tests must force;
3. the pre-release checklist walked for the changed surface;
4. every claim assigned an evidence state and bound to the exact subject tested;
5. every touched sibling-skill boundary and exception closed under the
Release Decision Gate below — never silently waived.
When to Use
Use this skill when:
- planning tests for a backend feature and choosing the test pyramid shape;
- building test data that respects constraints, tenancy, and privacy;
- writing concurrency tests that force real interleavings with barriers;
- designing failure tests: crashes between steps, dependency outages, malformed inputs;
- defining load/performance tests with realistic targets, sustained soak, and burst;
- investigating or preventing performance regressions;
- validating scaling behavior and limit assumptions;
- checking resource management: pools, file descriptors, memory, cleanup;
- evaluating compression trade-offs for payloads and storage;
- walking the cross-cutting pre-release checklist;
- reviewing a release exception, waiver, risk acceptance, or "ship anyway" request;
- reviewing whether a change is actually production-ready.
What ships with it
12 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.
- agents/openai.yaml 336 B
- examples/worked-example-payment-retry-release.md 5.8 KB
- references/papers/090-testing-foundations.md 32 KB
- references/papers/091-test-data.md 30 KB
- references/papers/092-concurrency-testing.md 32 KB
- references/papers/093-failure-testing.md 31 KB
- references/papers/094-load-and-performance-testing.md 34 KB
- references/papers/095-performance-engineering.md 35 KB
- references/papers/096-scalability.md 35 KB
- references/papers/109-resource-management.md 32 KB
- references/papers/117-compression.md 34 KB
- references/papers/146-cross-cutting-implementation-checklist.md 39 KB
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.
- today Changed · +5 lines · +17 tokens per session 2869b7e40205
- 5d ago First seen · 193 lines · 86 tokens per session scan A 1c2e4c9f1931
quality-release is a skill published in the GitHub repository d4rkNinja/arcforge (16 stars, last pushed yesterday), licensed MIT. It adds 103 tokens to every session and 3,713 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
release
Guide through the Cortex TMS release process — version bump, changelog, sync, tag, publish. Every step requires user approval.
generate-release-changelog
Generate a polished changelog for the latest Git tag. Classifies commits by impact, adds product and technical perspective, and prints the result directly in chat. Triggers on /generate-release-changelog or requests to generate/draft a changelog for the latest release.
git-flow-pr
Executes the full PR-driven development workflow: create an isolated feature branch from the current work, commit all staged changes, rebase cleanly onto the selected base branch (skipping any ancestor commits already merged), push the branch, and open a GitHub pull request linked to a related issue. Includes guidance…
write-changelog
Generates a CHANGELOG.md entry for a release by summarizing git commits since the last tag. Groups changes by type: Added, Changed, Fixed, Removed. Follows Keep a Changelog format (https://keepachangelog.com). Invoked when the user asks to update the changelog, write release notes, or prepare a release.
release
This skill should be used when the user asks to "release", "create a release", "ship it", "publish a new version", "bump version and release", "cut a release", or mentions releasing to GitHub/npm/PyPI. Orchestrates the full release pipeline from pre-flight checks through GitHub release creation.
preflight-check
This skill should be used when the user asks to "pre-flight check", "validate before commit", "validate before PR", "validate before deploy", "is this ready to ship", "check readiness", "run pre-flight", "validate project state", or wants context-aware validation across commit/PR/release/deploy boundaries.…