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/potapenko/spec-first-bootstrap/agents-mdgit clone --depth 1 https://github.com/potapenko/spec-first-bootstrapWhat 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 | $0.02811 | $0.02811 |
| Opus 5 | $0.01406 | $0.01406 |
| Sonnet 5 | $0.00562 | $0.00562 |
| Haiku 4.5 | $0.00281 | $0.00281 |
Grade A, and why
spec-first-bootstrap 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 — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file defines workflow rules for agents maintaining this repository.
It is not the source of truth for detailed product behavior. Product behavior
belongs in docs/specs/; portable installer doctrine belongs in
docs/agent-governance/.
Current branch only
Agents must work only in the Git branch that is checked out when the task begins.
Do not create, switch, rename, or publish another branch, and do not create a Git worktree, unless the user explicitly asks for it. General approval to begin work, commit, or push is not permission to create a branch.
Before editing, a required plan declares either a bounded task-owned write set or task-wide repository authority. Existing changes are blockers only where they overlap paths the task must modify. Leave all other changes untouched and exclude them from staging and commits.
Work is not complete or accepted while its changes exist only in another branch or worktree. Task changes must be integrated into the operator-selected current branch.
At the end of any task that changes files, create a checkpoint commit and push it from the currently checked-out branch. Before committing, verify that a safe, writable upstream exists and that the push will not publish unrelated local commits. If either condition cannot be established, do not create the checkpoint commit. Commit only the files you changed for the task, and leave unrelated working-tree changes untouched. Do not report the task as complete until both the checkpoint commit and push succeed.
Task framing and scope control
New-chat first implementation request gate
This gate applies only to the first implementation-bearing request in a new chat: a request that asks to modify code, task artifacts, or external state.
A request whose requested result is itself a plan is planning-only, including when the user asks to save that plan in a file for a future goal. Perform the bounded planning work and produce or save the requested plan directly. Do not first propose a meta-plan or ask for approval merely to create the plan. This does not authorize implementation of the work described by that plan.
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 · 284 lines · 2,811 tokens per session scan A ac8e069098dd
spec-first-bootstrap AGENTS.md is an instructions file published in the GitHub repository potapenko/spec-first-bootstrap (11 stars, last pushed 6d ago), licensed MIT. It adds 2,811 tokens to every session, about $0.0141 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
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.
buildNext
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).
spec-kit 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
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.