Borrowing it
Nothing to install: this file belongs to dadion123/agent-context-doctor. 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/dadion123/agent-context-doctor/main/AGENTS.mdgit clone --depth 1 https://github.com/dadion123/agent-context-doctorWrote 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/dadion123/agent-context-doctor/agents-md)<a href="https://agentmods.dev/instructions/dadion123/agent-context-doctor/agents-md"><img src="https://agentmods.dev/badge/instructions/dadion123/agent-context-doctor/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/dadion123/agent-context-doctor/agents-md"><img src="https://agentmods.dev/badge/instructions/dadion123/agent-context-doctor/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 | $0.00278 | $0.00278 |
| Opus 5.5 | $0.00111 | $0.00111 |
| Sonnet 5.5 | $0.00056 | $0.00056 |
| Haiku 4.5 | $0.00028 | $0.00028 |
Grade A, and why
agent-context-doctor 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 2mo 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
Agent Notes
Agent Context Doctor is a TypeScript / Node.js CLI. Keep changes small, deterministic, and safe by default.
Public identity:
- GitHub repository:
dadion123/agent-context-doctor - npm package:
agent-context-doctor
Commands
- Install:
pnpm install - Test:
pnpm test - Build:
pnpm build - Dev scan:
pnpm dev -- scan . - JSON scan:
pnpm dev -- scan . --json - Built CLI scan:
pnpm start -- scan . - CI scan:
pnpm start -- ci . --min-score 80
Product Direction
- This project is doctor-first, not generator-first.
- Prefer deterministic checks before LLM-assisted features.
- Keep
AGENTS.mdshort and move long explanations intodocs/. - Default to dry-run plans for fixes; require explicit user intent before writing.
- Never print
.envcontents or secrets. - User-facing explanations should be Japanese by default when working with Japanese users.
Maintainer Workflow
- PR review should focus on behavior, safety, and tests.
- Issue triage should separate bugs, rule ideas, docs gaps, and ecosystem compatibility requests.
- Release work should confirm tests, build output, README examples, and package metadata before external publication.
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.
- 2mo ago First seen · 34 lines · 278 tokens per session scan A 53bdcc52e6c9
agent-context-doctor AGENTS.md is an instructions file published in the GitHub repository dadion123/agent-context-doctor (1 stars, last pushed 4mo ago), licensed MIT. It adds 278 tokens to every session, about $0.0011 per session on Opus 5.5. 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.
agent-context-doctor AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agent-context-doctor AGENTS.mddadion123/agent-context-doctor | Instructions file | 1 | 4mo ago | MIT | A | 278 | Codex, OpenCode |
| ai-agent-rules-generator agent-observations.instructions.mdsavedpixel/ai-agent-rules-generator | Instructions file | 8 | 6mo ago | MIT | A | 1,787 | GitHub Copilot |
| ai-agent-rules-generator doc-sync.instructions.mdsavedpixel/ai-agent-rules-generator | Instructions file | 8 | 6mo ago | MIT | A | 1,652 | GitHub Copilot |
| ruleProb copilot-instructions.mdcanblmz1/ruleProb | Instructions file | 7 | 5mo ago | MIT | A | 19 | GitHub Copilot |
| ai-agent-rules-generator ratelimitting.instructions.mdsavedpixel/ai-agent-rules-generator | Instructions file | 8 | 6mo ago | MIT | A | 522 | GitHub Copilot |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |