Sighthound AGENTS.md

Repository instructions for Sighthound, a Rust and Python/Django project with automated checks for formatting, tests, security, complexity, and acceptance behaviour.

In plain words
What is it for?
Use them when modifying the project, running its test or quality gates, auditing dependencies, or preparing code for a push.
Why use it?
They show which checks must run after changes and help catch bugs, unsafe dependencies, and overly complex code.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/corgea/sighthound/agents-md
Clone the repo
git clone --depth 1 https://github.com/Corgea/Sighthound

Made for: Codex, OpenCode.

Per session 847 This file is loaded in full into every session.
When invoked 847 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 3d ago against content hash 915fe6681428, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

AGENTS.md · 47 lines

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 --enforce to hard-fail). Requires uvx on 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 with target/llvm-cov/lcov.info). Add --enforce to 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 against tests/features/ (warns and skips with no .feature files)
  • 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 against arch.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-hooks to 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

Read the full file on GitHub · 47 lines

Changes

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.

  1. 3d ago First seen · 47 lines · 847 tokens per session scan A 915fe6681428

Subscribe to this mod's changes

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.