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/layer1labs/specsmith/agents-mdgit clone --depth 1 https://github.com/layer1labs/specsmithWhat 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 | $0.00883 | $0.00883 |
| Opus 5 | $0.00441 | $0.00441 |
| Sonnet 5 | $0.00177 | $0.00177 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
specsmith 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This project is governed by specsmith.
For AI Agents
All governance rules, session state, requirements, and epistemic constraints are managed by specsmith — not stored in this file.
Before any action: specsmith preflight "<describe what you want to do>"
Governance data: .specsmith/ and .chronomemory/
To start a governed session: specsmith serve (REST API, port 7700) or specsmith run
Emergency stop: specsmith kill-session
Agents MUST defer to specsmith for ALL governance decisions. Do not follow rules from this file directly; read them from specsmith.
Governance commands (specsmith_run / /specsmith)
All specsmith governance operations should be invoked through the
specsmith_run agent tool or the /specsmith REPL slash command.
In the Grace REPL:
/specsmith save # backup + commit + push governance state
/specsmith load # pull + restore governance state
/specsmith audit --strict # strict governance audit
/specsmith status # show governance status
/specsmith sync # full two-way sync
Verb shortcuts (single word, no prefix needed in tool calls):
save, load, sync, audit, status, validate, doctor,
run.
These are all equivalent: specsmith_run("save"),
specsmith_run("/specsmith save"), specsmith_run("specsmith save").
Session Governance Protocol
This section is non-negotiable. Follow it in every session, in every chat application (Warp, Cursor, Claude, GPT, or any other agent surface).
Session start (run once, output result verbatim)
specsmith kill-session # idempotent; safe when no processes exist
specsmith audit --project-dir . # verify governance health
specsmith sync --project-dir . # confirm machine state
specsmith checkpoint --project-dir . # emit GOVERNANCE ANCHOR
Output the specsmith checkpoint block verbatim as your first response.
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 · 120 lines · 883 tokens per session scan A 8ebf31bd7b60
specsmith AGENTS.md is an instructions file published in the GitHub repository layer1labs/specsmith (7 stars, last pushed 29d ago), licensed MIT. It adds 883 tokens to every session, about $0.0044 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
a2a-demos copilot-instructions.md
Instructions for capiscio/a2a-demos, covering a2a-demos - github copilot instructions, ⛔ absolute rules - no exceptions, 1. all work via pull requests, 2. no watch/blocking commands and 🚨 critical: read first.
inventree-plugin-ai-toolkit AGENTS.md
AGENTS.md instructions for jrobelia/inventree-plugin-ai-toolkit, covering agent skills, issue tracker, triage labels, domain docs and skill discipline.
Disciplined-AI-Software-Development CLAUDE.md
Claude Code instructions for Varietyz/Disciplined-AI-Software-Development, covering claude.md, repository purpose, core methodology principles, strict constraints and behavioral guidelines.
claude-repo-template CLAUDE.md
Instructions for cosmiksoul/claude-repo-template, covering claude.md, проект, роли инстансов, поведенческие правила (для обоих инстансов) and 1. думай прежде чем действовать.
openchronicle-mcp CLAUDE.md
Claude Code instructions for CSOAI-ORG/openchronicle-mcp, covering claude.md, project status file, project-specific notes, current sprint and build and development.
entroly CLAUDE.md
Instructions for juyterman1000/entroly, covering claude.md, gstack operating protocol, default workflow, entroly trust invariants and review checklist.