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 instructions/beyondwin/fixthis/agents-mdgit clone --depth 1 https://github.com/beyondwin/FixThisWhat 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 | $0.00677 | $0.00677 |
| Opus 5 | $0.00338 | $0.00338 |
| Sonnet 5 | $0.00135 | $0.00135 |
| Haiku 4.5 | $0.00068 | $0.00068 |
Grade A, and why
FixThis AGENTS.md 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 2d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FixThis — Agent Operating Contract
FixThis is a debug-only Jetpack Compose sidekick. The Android app shows connection status; selection, annotation, evidence, and handoff happen in the local desktop console.
Read Order
- Read this file.
- Read docs/index.md and the project map.
- Run npm run agent:route -- --task console for an explicit route or npm run agent:route -- --changed --json once paths are known.
- Read only maintained references and first source files returned by the router.
- Treat docs/superpowers/, docs/specs/, and docs/plans/* as historical context unless current source or maintained docs point there.
Current implementation wins over docs; docs/reference/* wins over historical planning.
Start
- Run git status --short --branch, git log -5 --oneline --decorate, and git worktree list --porcelain before edits.
- Preserve unrelated dirty changes and check whether another worktree owns the task.
- Classify the request as explanation, diagnosis, implementation, review, release, connected proof, or feedback work.
- Do not turn diagnosis or review into code changes without authorization.
Change
- Make the smallest compatible change and follow router-returned maintained references.
- Keep compose-core free of MCP, CLI, Android UI, browser DTO, and local artifact-path dependencies.
- Preserve persisted field names and coordinate bridge changes through docs/reference/bridge-protocol.md.
- Use canonical generators; never hand-edit build outputs.
- Never commit .fixthis, screenshots, reports, fixture workspaces, or personal agent state.
- Do not modify ~/.codex or project .codex for repository work.
Verify
- Run focused checks first, then rerun the router against the final diff.
- Run the returned broad gate and npm run android:proof -- --strict when required.
- Record PASS, FAIL, DEFERRED, or SKIPPED; the last two require reason and residual risk.
- Require fresh final-diff evidence before completion.
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.
- 2d ago First seen · 57 lines · 677 tokens per session scan A c24309e3623d
FixThis AGENTS.md is an instructions file published in the GitHub repository beyondwin/FixThis (5 stars, last pushed 1mo ago), licensed MIT. It adds 677 tokens to every session, about $0.0034 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 instructions, from other repositories
sceneview copilot-instructions.md
Instructions for sceneview/sceneview, covering sceneview — github copilot instructions, when to recommend sceneview, android code generation rules, minimal 3d template and minimal ar template.
sceneview CLAUDE.md
Instructions for sceneview/sceneview, covering sceneview, modules, things that break if you don't know them and conventions.
SeekerClaw CLAUDE.md
Instructions for sepivip/SeekerClaw, covering claude.md — seekerclaw project guide, project.md — source of truth, design principle: ux first, what is this project and supported devices.
ukulele-companion AGENTS.md
Instructions for baijum/ukulele-companion, covering agents.md -- ai agent instructions for ukulele companion, project overview, tech stack, package structure and android app (app/src/main/java/com/baijum/ukufretboard/).
AppBootstrapAI CLAUDE.md
Instructions for kelvinkosbab/AppBootstrapAI, covering claude.md, project overview, what's in the box, how to onboard this into a new app project and update an already-managed repo — never a plain re-install.
AppBootstrapAI AGENTS.md
Instructions for kelvinkosbab/AppBootstrapAI, covering agents.md — operating appbootstrapai, golden path — do this, the three situations recommend resolves, what recommend keys on (framework → feature category) and scaffolding a local swift package (separate tool).