Borrowing it
Nothing to install: this file belongs to mianbaofang/exam-revision-handbook. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mianbaofang/exam-revision-handbook/main/AGENTS.mdgit clone --depth 1 https://github.com/mianbaofang/exam-revision-handbookWrote 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/instructions/mianbaofang/exam-revision-handbook/agents-md)<a href="https://agentmods.dev/instructions/mianbaofang/exam-revision-handbook/agents-md"><img src="https://agentmods.dev/badge/instructions/mianbaofang/exam-revision-handbook/agents-md/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.
<a href="https://agentmods.dev/instructions/mianbaofang/exam-revision-handbook/agents-md"><img src="https://agentmods.dev/badge/instructions/mianbaofang/exam-revision-handbook/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00696 | $0.00696 |
| Opus 5 | $0.00348 | $0.00348 |
| Sonnet 5 | $0.00139 | $0.00139 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
exam-revision-handbook 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 10d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Agent Guidance
Start Here
Read PROJECT.md before making changes. Then read:
skills/exam-revision-handbook/SKILL.mdreferences/workflow-contract.mdreferences/revision_guide_spec.mddocs/ARCHITECTURE_DECISION_SKILL_WORKFLOW.mddocs/PROJECT_OPERATIONS.md
Single Canonical Skill
skills/exam-revision-handbook/SKILL.mdis authoritative and is the GitHub CLI automatic-discovery entry.- GitHub
main, the matching tag, and its Release download are one current standard Skill release. The ZIP is the downloadable form of that release, never another edition, structure, or development line. - Do not recreate the retired
skill/workflow, a root-level wrapperSKILL.md, or another nested workflow. src/andtests/are development support for the same standard Skill, not a legacy product.- The installable ZIP is built from an allowlist and must keep one top-level
exam-revision-handbook/folder with exactly oneSKILL.md.
Product Boundaries
- Keep rules independent of provider, qualification, subject, and batch size.
- Python may acquire evidence, validate structure, render, hash, record, and block. It must not replace LLM syllabus analysis, teaching writing, visual judgment, semantic review, or approval.
- The first-turn visual-capability question is a blocking preflight field. Do not infer an answer or silently select local image generation.
- Render and fully review HTML before PDF export. Machine diagnostics cannot approve a handbook.
- Every handbook in a batch requires an independent full review and delivery record.
Change Discipline
- Make the smallest change that satisfies the current request.
- Preserve unrelated user changes and public assets.
- Update
CHANGELOG.mdfor every completed iteration. - Keep the canonical Skill, references, Agent metadata, evals, README files, and tests in sync when their shared contract changes.
- If engine behavior changes, rebuild and re-lock the embedded Wheel. A source change without a matching runtime asset is incomplete.
- Do not include generated outputs, official PDFs, caches, local paths, private notes, promotional MP4 files, or review scratch data in commits or Releases.
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.
- 10d ago First seen · 78 lines · 696 tokens per session scan A afee2f7dd4dd
exam-revision-handbook AGENTS.md is an instructions file published in the GitHub repository mianbaofang/exam-revision-handbook (2 stars, last pushed 24d ago), licensed MIT. It adds 696 tokens to every session, about $0.0035 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.