Borrowing it
Nothing to install: this file belongs to wlfghdr/agentic-kb. 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/wlfghdr/agentic-kb/main/AGENTS.mdgit clone --depth 1 https://github.com/wlfghdr/agentic-kbWrote 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/wlfghdr/agentic-kb/agents-md)<a href="https://agentmods.dev/instructions/wlfghdr/agentic-kb/agents-md"><img src="https://agentmods.dev/badge/instructions/wlfghdr/agentic-kb/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/wlfghdr/agentic-kb/agents-md"><img src="https://agentmods.dev/badge/instructions/wlfghdr/agentic-kb/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 | $0.01080 | $0.01080 |
| Opus 5.5 | $0.00432 | $0.00432 |
| Sonnet 5.5 | $0.00216 | $0.00216 |
| Haiku 4.5 | $0.00108 | $0.00108 |
Grade A, and why
agentic-kb 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 6d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
This file is read first by any AI agent (and any human) working in this repository. It defines the ground rules. Layer-specific documents in docs/ extend these rules — they never override them.
This repo is a specification, not a product. Work done here is documentation work: precise, versioned, cross-referenced. Code exists only to validate docs (CI).
Rules
1. Spec-first, implementation-later
This repo defines what the system does and how it is shaped. It does not build it. Implementations live in companion repos. If a PR here proposes runtime code beyond CI tooling, reject it.
2. No vendor lock-in
The spec must remain IDE-agnostic, harness-agnostic, and vendor-neutral. Examples are welcome. Hardcoded product names, company names, or proprietary service references are not. The CI guards against a small list of forbidden terms; reviewers guard against the rest.
3. Git is the change record
Docs, skills, agents and templates carry no version numbers, dates, or changelog sections, and neither do the KB artifacts the spec defines. Git history and PR review are the per-file record; CI (scripts/check_no_file_versioning.py) rejects reintroduced versioning.
- Use a Conventional Commit PR title (
fix:,docs:,feat:,feat!:for breaking spec changes). PRs are squash-merged and the title becomes the release note. - Never edit the root
VERSION, the plugin manifest versions, or the rootCHANGELOG.mdin a change PR. release-please generates them in its release PR.
4. Cross-references stay live
Every link in a spec doc must resolve. CI enforces this via lychee (external) and scripts/check_consistency.py (internal). Broken links = red CI = not done.
5. Lean over exhaustive
A spec section that says the same thing three times is worse than one that says it once. When in doubt, cut. Examples belong in docs/examples/, not inline.
6. CI green is the definition of done
No PR is ready for review until CI is green. A red main is the top-priority fix for maintainers. Never skip hooks; never merge with failing checks.
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.
- 6d ago Changed · -46 lines · -2,209 tokens per session 1110fd5b48d9
- 1mo ago First seen · 128 lines · 3,289 tokens per session scan A f81b0194c3a4
agentic-kb AGENTS.md is an instructions file published in the GitHub repository wlfghdr/agentic-kb (10 stars, last pushed 6d ago), licensed Apache-2.0. It adds 1,080 tokens to every session, about $0.0043 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.
Other instructions, from other repositories
runtm copilot-instructions.md
Copilot instructions for runtm-ai/runtm, covering runtm tool instructions, critical rules, structure, adding endpoints and app/api/v1/myendpoint.py.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).