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/corgea/sighthound/agents-mdgit clone --depth 1 https://github.com/Corgea/SighthoundWhat 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 | $0.00847 | $0.00847 |
| Opus 5 | $0.00424 | $0.00424 |
| Sonnet 5 | $0.00169 | $0.00169 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
Sighthound 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 3d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE
Commands
make targets delegate to the cargo harness runner (harness.rs). Pass tunable
flags (--min, --max, --enforce) by invoking the runner directly, e.g.
cargo harness crap --enforce.
- After edits:
make check— fix, format, lint, test, suppression report - Pre-commit:
make pre-commit— staged Rust files only (auto via git hook) - Pre-push:
make pre-push— read-only push gate: clippy + format check → acceptance → arch (auto via git hook; validates the whole pushed tree) - CI:
make ci— strict pipeline: clippy → format check → audit → complexity → tests → acceptance → coverage → crap → arch. CRAP is advisory (warns only — pass--enforceto hard-fail). Requiresuvxon PATH. - Complexity:
make complexity— [email protected] CC gate (CCN≤15, args≤8, length≤100) over src + tests - CRAP (advisory):
cargo harness crap --max=30— complexity × coverage gate (joins lizard --csv withtarget/llvm-cov/lcov.info). Add--enforceto exit 1 on offenders (default exits 0 with warning). - Audit:
make audit— audit dependencies for known vulnerabilities (via cargo-audit) - Acceptance:
make acceptance— run cucumber againsttests/features/(warns and skips with no.featurefiles) - Coverage:
cargo harness coverage --min=0— cargo-llvm-cov line coverage with threshold - Mutation (advisory):
make mutation— cargo-mutants kill-rate on the crate - Arch:
make arch— cargo-modules checks againstarch.toml - Agents drift:
make agents-md-drift— fail if the local CLAUDE.md mirror differs from AGENTS.md (AGENTS.md is the committed source; edit it, not CLAUDE.md) - Sync:
make sync-agents-md— rewrite the git-ignored CLAUDE.md mirror from AGENTS.md - Setup:
make setup-hooksto install git pre-commit + pre-push hooks and materialize the git-ignored agent files (CLAUDE.md mirror plus the.claude/+.codex/Stop hook wiring) - Stop hook: auto-formats/fixes changed files, then runs complexity and CRAP (
make stop-hook)
Python / Django test naming
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.
- 3d ago First seen · 47 lines · 847 tokens per session scan A 915fe6681428
Sighthound AGENTS.md is an instructions file published in the GitHub repository Corgea/Sighthound (279 stars, last pushed 6d ago), licensed MIT. It adds 847 tokens to every session, about $0.0042 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 2026-08-30.
Other instructions, from other repositories
glyph CLAUDE.md
Instructions for benmyles/glyph, covering claude.md, project overview, installation, macos and architecture.
local-testing-agent CLAUDE.md
Claude Code instructions for marcelkurvers/local-testing-agent, covering claude.md, architecture, two main entry points, key differences and development commands.
appwrite AGENTS.md
AGENTS.md instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
awesome-go AGENTS.md
AGENTS.md instructions for avelino/awesome-go, covering awesome-go · llm contribution guide, project snapshot, when modifying the awesome list, coding guidelines and testing & validation.
azure-sdk-for-go go-code.instructions.md
Instructions for Azure/azure-sdk-for-go: All code should follow the guidelines from the Azure Go SDK Guidelines. This document is a summary of the most important guidelines to follow when contributing to the Azure Go SDK.
ai AGENTS.md
AGENTS.md instructions for vercel/ai, covering agents.md, project overview, repository structure, key directories and core package dependencies.