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/jiezeng2004-design/patchwarden/agents-mdgit clone --depth 1 https://github.com/jiezeng2004-design/PatchWardenWrote 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/jiezeng2004-design/patchwarden/agents-md)<a href="https://agentmods.dev/instructions/jiezeng2004-design/patchwarden/agents-md"><img src="https://agentmods.dev/badge/instructions/jiezeng2004-design/patchwarden/agents-md.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 | $0.00539 | $0.00539 |
| Opus 5 | $0.00269 | $0.00269 |
| Sonnet 5 | $0.00108 | $0.00108 |
| Haiku 4.5 | $0.00054 | $0.00054 |
Grade A, and why
PatchWarden 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 4d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PatchWarden agent rules
PatchWarden is a security-focused local MCP bridge. Preserve workspace confinement, command allow-lists, sensitive-file blocking, explicit agent registration, and auditable task artifacts.
Commands
Run from this repository in Windows PowerShell with npm.cmd:
npm.cmd ci
npm.cmd run build
npm.cmd test
npm.cmd run test:mcp
npm.cmd run test:http-mcp
npm.cmd run doctor:ci
npm.cmd run pack:clean
npm.cmd run verify:package
Use the narrowest relevant smoke test during iteration, then run the full chain before release or security-sensitive changes.
Use npm.cmd run doctor instead of doctor:ci when validating a configured local runtime.
Safety contracts
- Do not expose a general-purpose remote shell or weaken exact command matching.
- Keep all repo paths under configured
workspaceRoot; block sensitive names and out-of-workspace changes. - Do not read or persist tokens, cookies, browser state,
.env, SSH keys, or credential files. - Do not blanket-kill watchers or tunnels. Only launcher-owned processes may be supervised.
- Keep live tunnel/watcher cutover separate from local code verification; do not restart live services unless explicitly requested.
- Preserve structured task evidence, heartbeat state, before/after Git snapshots, changed-file records, and redaction.
Changes and release
- Add or update smoke coverage for changed behavior.
- Keep README, examples, tool manifests, package metadata, and migration docs aligned.
- Use branch -> PR -> CI -> merge. Publishing is manual and must separately verify GitHub Release,
patchwardenon npm, anddist-tags.latest. - The pre-rename npm package is frozen; do not publish new versions under the legacy name.
Codex Memory
本项目的长期记忆库位于：
D:\ai_agent\CodexMemory
处理复杂任务前请先阅读：
D:\ai_agent\CodexMemory\04_Index\00_INDEX.mdD:\ai_agent\CodexMemory\00_Workspace\CURRENT.mdD:\ai_agent\CodexMemory\03_Permanent\Projects\PatchWarden.md
如果本次任务产生长期有效结论，请更新对应项目记忆。 如果本次任务出现可复用修复经验，请记录到 Bugs_and_Fixes。 如果本次任务出现失败尝试，请记录到 Failed_Attempts。 如果本次任务形成稳定部署流程，请记录到 Runbooks。 禁止记录真实 API Key、Token、Cookie、密码、私钥。
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.
- 4d ago First seen · 56 lines · 539 tokens per session scan A 175ced9ec7c4
PatchWarden AGENTS.md is an instructions file published in the GitHub repository jiezeng2004-design/PatchWarden (5 stars, last pushed 4d ago), licensed MIT. It adds 539 tokens to every session, about $0.0027 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
enquire-mcp AGENTS.md
AGENTS.md instructions for oomkapwn/enquire-mcp, covering agents.md, tl;dr, architecture (5-minute orientation), conventions and typescript.
mcp-app-typescript-template AGENTS.md
AGENTS.md instructions for pomerium/mcp-app-typescript-template, covering repository guidelines, project overview, development commands, quick start and all available commands.
Local-Codex-Bridge AGENTS.md
Instructions for zoeynine/Local-Codex-Bridge, covering ai agent guidance, project intent, architecture, security and permission boundaries and adapting to another machine.
ThreeBrowserStudio AGENTS.md
AGENTS.md instructions for SamG-Coder/ThreeBrowserStudio: ThreeBrowser Studio is an LLM-first authoring runtime. MCP is the editor and the native WebGPU window is the shared live viewport. Preserve that product shape: do not grow a conventional inspector-heavy browser UI.
sdk CLAUDE.md
Claude Code instructions for WaniWani-AI/sdk, covering waniwani sdk, public api tiers, oss (no api key required), free tier (one env var: waniwaniapikey) and internal (not part of the public api).
toon-memory AGENTS.md
Instructions for LuiggiVal08/toon-memory, covering agents.md, build & verify, architecture, smarter memory pattern and visual memory pattern.