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/henryh/ai-specdoc/agents-mdgit clone --depth 1 https://github.com/henryh/AI-SpecDocWrote 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/henryh/ai-specdoc/agents-md)<a href="https://agentmods.dev/instructions/henryh/ai-specdoc/agents-md"><img src="https://agentmods.dev/badge/instructions/henryh/ai-specdoc/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 | $0.00496 | $0.00496 |
| Opus 5 | $0.00248 | $0.00248 |
| Sonnet 5 | $0.00099 | $0.00099 |
| Haiku 4.5 | $0.00050 | $0.00050 |
Grade A, and why
AI-SpecDoc 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 5d 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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Instructions
This file contains project-specific workflow and rules. Role-specific agent instructions live in the AI skill files; do not duplicate them here.
References
- Project docs index:
docs/index.md - Development workflow:
docs/development.md - Task management workflow:
docs/task-management.md
Persistence Policy
- Any system/developer instructions or other critical workflow rules must be recorded in persistent files (project docs or role skill files), not only in-session context.
- When such instructions are discovered during a session, update the relevant files so a new session can resume without loss.
Git Workflow (Project)
Follow the repository Git rules in docs/development.md (branch naming, commit rules, merge policy).
Post-Completion Merge Request (Hard Stop)
- After successfully completing a task on a task branch (and committing task-related changes), the final response must explicitly request user approval to merge into
main. - Do not treat task completion, "finish", or a status summary as merge approval.
- Do not end a successful task handoff with only "done/completed" status; include a direct merge approval prompt (for example: "Approve merge to
main?").
Agent Console Logs
- When switching skill modes during task work, emit a console message that states the current agent and who invoked it (e.g., "Console: feature-developer invoked by user.") so the terminal log captures the handoff.
Pre-flight Branch Check (Hard Stop)
- Before any code or configuration changes, confirm you are on a task branch (not main) and that it follows /-.
- Documentation files, AGENTS.md, and task files under tasks/** may be edited on main only for standalone documentation/process maintenance not tied to an active task.
- If the user starts or continues a task from tasks/active.json, create/switch to a task branch before any edits, even when the first edits are only in docs/** or tasks/**.
- Still run git branch --show-current and git status before edits; if task-related changes are needed while on main, create a task branch that follows the naming rule (default type to feat if unclear) and continue without asking for the branch name.
- If user edits are present in files you are about to modify for the current task, ask whether to keep or overwrite those edits before applying changes that could replace them.
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.
- 5d ago First seen · 31 lines · 496 tokens per session scan A b52f9832d7f5
AI-SpecDoc AGENTS.md is an instructions file published in the GitHub repository henryh/AI-SpecDoc (2 stars, last pushed 6mo ago), licensed MIT. It adds 496 tokens to every session, about $0.0025 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).