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/randomittin/heimdall/agents-mdgit clone --depth 1 https://github.com/randomittin/heimdallWhat 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 | $0.01020 | $0.01020 |
| Opus 5 | $0.00510 | $0.00510 |
| Sonnet 5 | $0.00204 | $0.00204 |
| Haiku 4.5 | $0.00102 | $0.00102 |
Grade A, and why
heimdall 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 2d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working in the Heimdall repo
Heimdall is the watchman: it gates other people's repos. So the bar here is the bar we sell. Read this before your first edit.
The rules that actually block you
- No stub, placeholder, TODO, or skeleton code. A
PreToolUsehook scans every Claude Code write for unfinished code shapes (empty bodies, not-implemented throws,# TODOcomments) and refuses the write — but that hook only fires inside a live Claude Code session.bin/heimdall-gate-run'spre-commitphase backs it up at the git layer: it re-scans the staged diff against the same shared shapes (bin/lib/heimdall-stub-patterns.sh), so the ban holds no matter which tool — or human — makes the commit. If you cannot implement something fully, say so — faking it is the one failure mode this repo exists to catch. - Tests are bash. One file per surface:
test/<name>.test.sh, run withbash test/<name>.test.sh. Exit 0 = green. A test printsPASS/FAILlines and a count. Follow the shape of a neighbouring test rather than inventing a harness. - Every assertion must be falsifiable. Before you call a test done, break the thing it covers and watch it go RED, then revert and watch it go GREEN. A test that cannot fail is not a gate — it is decoration.
- Quality gates run before push (
heimdall-state check-quality-gates): tests green, lint clean, no untested changes.
Environment
- bash 3.2.57 on macOS.
timeout(1)does not exist — useperl -e 'alarm N; exec @ARGV' -- <cmd>. - Tests must be hermetic: redirect
HOME, work inmktemp -d, never touch the real~/.heimdalland never reach a live control plane. - Nothing here is submitted to an external service during a test run. Local artifacts only.
Conventions
- Generated regions in tracked files live between
HEIMDALL:<NAME>:BEGIN/HEIMDALL:<NAME>:ENDmarkers and are written by a renderer, never by hand — seebin/heimdall-render-version(README version region) andbin/heimdall-init(the AGENTS.md fence below). Match that pattern; do not invent a second one. - Version truth is
.claude-plugin/plugin.json.version. Every other surface is rendered from it. - Independent work runs in parallel: batch independent tool calls into one message, and give each parallel agent its own file scope.
- One completed task = one atomic commit, conventional prefix.
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.
- 2d ago First seen · 74 lines · 1,020 tokens per session scan A e2ecdf3e1bce
heimdall AGENTS.md is an instructions file published in the GitHub repository randomittin/heimdall (5 stars, last pushed 12d ago), licensed MIT. It adds 1,020 tokens to every session, about $0.0051 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
pg-aiguide CLAUDE.md
Claude Code instructions for timescale/pg-aiguide, covering tiger docs mcp server - development guidelines, build, test & run commands and code style guidelines.
pdlc-skills CLAUDE.md
Instructions for kanfu-panda/pdlc-skills, covering claude.md, repository purpose, repository layout, sub-skill naming and common commands.
claude-for-hk-law CLAUDE.md
Instructions for Buildwise-Studios/claude-for-hk-law, covering claude.md, layout, legal system context, key hong kong ordinances and legal research sources.
gandalf CLAUDE.md
Instructions for sebacaro/gandalf, covering gandalf — cli para spec driven development, comandos, activar entorno, ejecutar directamente and o con gandalf global (después de install.sh).
revogrid-mcp AGENTS.md
AGENTS.md instructions for revolist/revogrid-mcp, a project described as: RevoGrid MCP Service.
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).