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/beyondwin/fixthis/fixthis-release-maintenancenpx skills add beyondwin/FixThis --skill fixthis-release-maintenancegit clone --depth 1 https://github.com/beyondwin/FixThisWrote 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/beyondwin/fixthis/fixthis-release-maintenance)<a href="https://agentmods.dev/skills/beyondwin/fixthis/fixthis-release-maintenance"><img src="https://agentmods.dev/badge/skills/beyondwin/fixthis/fixthis-release-maintenance.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 | $0.00030 | $0.00284 |
| Opus 5 | $0.00015 | $0.00142 |
| Sonnet 5 | $0.00006 | $0.00057 |
| Haiku 4.5 | $0.00003 | $0.00028 |
Grade A, and why
fixthis-release-maintenance 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 3d 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
FixThis Release Maintenance
Use only for FixThis source checkout release work. Keep repository proof, connected Android proof, Git state, and public registry reality separate.
- Read
docs/contributing/release-readiness.md,docs/contributing/release-process.md, andCONTRIBUTING.md. - Run
npm run agent:route -- --task release --json. - Establish intended version and channels without changing them.
- Run
npm run release:realityand record exact registry, tag, and downstream evidence. - Run
npm run evidence:releasefor repository evidence. - Run
npm run android:proof -- --strict --continuewhen the contract requires connected proof. - Run
npm run release:checkbefore a release PR or tag. - Report PASS, FAIL, DEFERRED, and SKIPPED separately with reason and residual risk.
- Verify local HEAD, upstream, remote branch, tag, registry, and downstream state independently.
Tag, publish, push, or edit a downstream repository only when the user explicitly requests that state change. Never treat a proxy marker, cached page, deferred device check, or local commit as publication proof.
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.
- 3d ago First seen · 21 lines · 30 tokens per session scan A 03a0a935c969
fixthis-release-maintenance is a skill published in the GitHub repository beyondwin/FixThis (5 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 284 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.
Other skills, from other repositories
publish-release
Use this skill when users request to publish an release update.
release
Unified release for both Android and iOS from a single version tag. Runs quality gates, bumps both platform versions in one commit, tags, builds both platforms, uploads Android to Play Store, and opens iOS archive for App Store upload. Use when the user asks to release, ship, cut a release, or make a new version.
android-release
Build and upload an Android release based on an existing git tag. Runs lint and all tests first (unit and instrumented), bumps version to match the tag, builds release AAB and APK (without debug info), commits the version bump, and uploads the AAB to Google Play Store internal testing. Use when the user asks to make…
ios-release
Build an iOS release based on an existing git tag. Bumps version to match the tag, builds the shared KMP framework and the iOS app archive. Use when the user asks to make an iOS release, build for App Store, or create an iOS archive.
play-store-promote-public
Promote a release to Google Play open testing or production tracks. Supports full rollout and staged rollout to production. Use when the user asks to promote to open testing, beta, go to production, release to all users, staged rollout, or increase rollout percentage.
ios-appstore-publish
Publish the iOS app to Apple's App Store. Covers the full workflow from code signing setup through archive, upload, metadata, and submission. Use when the user asks to publish to App Store, submit for review, upload to App Store Connect, or distribute the iOS app.