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/heurema/signum/agents-mdgit clone --depth 1 https://github.com/heurema/signumWrote 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/heurema/signum/agents-md)<a href="https://agentmods.dev/instructions/heurema/signum/agents-md"><img src="https://agentmods.dev/badge/instructions/heurema/signum/agents-md.svg" alt="Measured on agentmods" 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 | $0.01452 | $0.01452 |
| Opus 5 | $0.00726 | $0.00726 |
| Sonnet 5 | $0.00290 | $0.00290 |
| Haiku 4.5 | $0.00145 | $0.00145 |
Grade A, and why
signum 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 4d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Purpose
- Give human and AI contributors a short map of the repo surfaces that matter first.
- Keep repo-specific working rules in one file and link to deeper docs instead of duplicating them.
- Make it obvious which changes are just docs, which change deterministic core behavior, and which change LLM orchestration.
Agent Entry Points
| Surface | Path | Role | Owner | Notes |
|---|---|---|---|---|
| Primary product entry point | commands/signum.md |
Canonical pipeline behavior (CONTRACT -> EXECUTE -> AUDIT -> PACK) |
@vi |
Source of truth for core Signum behavior |
| Init/bootstrap entry point | commands/init.md |
Bootstraps project.intent.md, project.glossary.json, and optional harness docs |
@vi |
Root variant; Claude overlay lives under platforms/claude-code/commands/init.md |
| LLM prompts | agents/ |
Contractor, engineer, reviewer, synthesizer, init synthesizer prompts | @vi |
Changes here affect agent behavior directly |
| Deterministic core | lib/ |
Shell checks, DSL runner, scanners, state/policy helpers | @vi |
Prefer tests for every behavioral change |
| Schemas and contracts | lib/schemas/ |
Contract / proofpack / modules schemas | @vi |
Treat schema changes as compatibility-sensitive |
| Platform overlays | platforms/ |
Surface-specific command/docs variants | @vi |
Root command/docs remain canonical unless an overlay deviation is explicitly documented |
| Codex plugin metadata | .agents/plugins/marketplace.json, .codex-plugin/plugin.json, platforms/codex/.codex-plugin/plugin.json, platforms/codex/SKILL.md |
Codex App marketplace, install manifest, and skill entry point | @vi |
Keep version aligned with .claude-plugin/plugin.json; Codex skill remains an overlay |
| OpenSpec workflow | openspec/config.yaml, .claude/commands/opsx/, .claude/skills/openspec-*/, .codex/skills/openspec-*/ |
Spec-driven change workflow and generated agent entry points | @vi |
Regenerate managed instructions with openspec update; review config changes before regeneration |
| Verification surface | tests/ |
Shell tests for deterministic behavior | @vi |
If a deterministic behavior changes, add/update a test |
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.
- 4d ago First seen · 69 lines · 1,452 tokens per session scan A 3374074af85f
signum AGENTS.md is an instructions file published in the GitHub repository heurema/signum (18 stars, last pushed 1mo ago), licensed MIT. It adds 1,452 tokens to every session, about $0.0073 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
river-review GEMINI.md
Gemini CLI instructions for s977043/river-review, covering gemini instructions (river-review), 必須チェック, gemini-specific tips, prompt assembly and development tips.
living-manual CLAUDE.md
Instructions for dougstanford/living-manual, covering living-manual, start of every session, how work lands — non-negotiable, user's manual (living-manual) and releasing.
ship-it open-pr.instructions.md
Instructions for khrichtchatyi/ship-it: When the user asks to open, create, or submit a pull request, follow the skill in skills/open-pr/SKILL.md in full: verify gh is authenticated, resolve the target repository and default branch, push the current branch, open one pull request with a title and body derived from the…
agent-skills CLAUDE.md
Instructions for mindbox-cloud/agent-skills, covering agent-skills — developer guide for claude code, repository purpose, repository structure, how to add a new plugin and step 1 — create the directory structure.
my-claude-skills CLAUDE.md
Instructions for brody-0125/my-claude-skills, covering claude code skills repository, validation commands, sub-kopring-engineer: kotlin/java 코드 컨벤션 검증, numerical: 수치 연산 코드 검증 and sub-test-engineer: 문서 일관성 검증.
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).