Borrowing it
Nothing to install: this file belongs to firelock-ai/kin. 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/firelock-ai/kin/main/AGENTS.mdgit clone --depth 1 https://github.com/firelock-ai/kinWrote 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/firelock-ai/kin/agents-md)<a href="https://agentmods.dev/instructions/firelock-ai/kin/agents-md"><img src="https://agentmods.dev/badge/instructions/firelock-ai/kin/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/firelock-ai/kin/agents-md"><img src="https://agentmods.dev/badge/instructions/firelock-ai/kin/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 | $0.01325 | $0.01325 |
| Opus 5.5 | $0.00530 | $0.00530 |
| Sonnet 5.5 | $0.00265 | $0.00265 |
| Haiku 4.5 | $0.00133 | $0.00133 |
Grade A, and why
kin 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 1mo 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kin
kin is the semantic system of record: repository format, CLI, daemon, MCP server, projections,
reconcile, review, provenance, execution, and the bundled crates and packages under crates/ and
packages/. Work belongs here when it changes local semantic repository truth, projections or
reconcile, CLI, daemon or MCP behaviour, or provenance, review and execution semantics. Graph
storage and retrieval live in the bundled crates/kin-db. Hosted collaboration lives in kinlab.
The graph is the authority
Runtime query paths answer from the graph. They never grep, walk or rank raw filesystem contents,
and scripts/zero_file_search_guard.sh enforces that. When the graph cannot produce an answer,
return an error or report the gap rather than falling back to raw file search. Ingestion, import,
reconcile, migration, projection, config and test IO may read files as explicit boundaries.
When the Kin MCP server is available, use it to read this repository. Find an entity with
semantic_search when you know its name or semantic_locate when you know only the behaviour,
then take get_context_pack on the best hit, and find_references or impact_analysis before
changing shared code. Read the _kin envelope on every answer, since an empty result is
trustworthy only when its negative.safe_to_conclude_absent says so.
docs/gemini-extension-context.md is the full tool guide, and
the Gemini CLI extension loads it as context.
Checks
CI runs these, and .github/workflows/ci.yml holds the current flags and the jobs that apply to
a change:
cargo fmt -- --check
cargo clippy --all-targets --all-features -- <the allow list ci.yml assembles>
cargo nextest run --locked --partition count:<n>/3 # three shards
cargo test --doc --locked # nextest does not run doctests
python3 scripts/check-quarantine.py
bash scripts/zero_file_search_guard.sh
Run targeted crate tests for a behaviour change, and leave the full-workspace run to CI. Set
KIN_EMBED_BACKEND=cpu for any gate. The default, auto, batches on the host's single Metal
device, and concurrent gates that share it fail on host load rather than on their diff. CPU and
Metal differ in the last ULPs of every vector, so a citable release-clean result never sets it.
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.
- 1mo ago Changed · +6 lines · +100 tokens per session 8570914414fd
- 1mo ago Changed · -17 lines · -314 tokens per session ba1feb85c1ff
- 1mo ago Changed · +23 tokens per session 3c04e89b8831
- 1mo ago Changed · +1 lines · +25 tokens per session a50fa51b6a17
- 1mo ago Changed · +1 lines · +7 tokens per session 731bd1104fb0
- 1mo ago Changed · +74 lines · +1,223 tokens per session a1680582118e
- 2mo ago First seen · 26 lines · 261 tokens per session scan A 8b9f930b1790
kin AGENTS.md is an instructions file published in the GitHub repository firelock-ai/kin (68 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,325 tokens to every session, about $0.0053 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 2026-08-30.
Other instructions, from other repositories
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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.