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/telus-labs/stagecraft/agents-mdgit clone --depth 1 https://github.com/telus-labs/stagecraftWrote 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/telus-labs/stagecraft/agents-md)<a href="https://agentmods.dev/instructions/telus-labs/stagecraft/agents-md"><img src="https://agentmods.dev/badge/instructions/telus-labs/stagecraft/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 | $0.01093 | $0.01093 |
| Opus 5 | $0.00547 | $0.00547 |
| Sonnet 5 | $0.00219 | $0.00219 |
| Haiku 4.5 | $0.00109 | $0.00109 |
Grade A, and why
stagecraft 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Host-neutral context for any LLM working on the Stagecraft codebase itself. (The CLI binary is devteam; the project is Stagecraft.) If you are using Stagecraft to drive another project's pipeline, read README.md instead.
Start here (in order)
CONTRIBUTING.md— setup, recipes for common changes, conventions, and the doc-update checklist.ARCHITECTURE.md— 15 locked design decisions. Do not break these casually.core/adapters/host-adapter.md— the contract every adapter must satisfy.docs/walkthroughs/stage-04-split-host.md— stress-test trace that locked the multi-workstream dispatch contract. Read before touching dispatch logic.
Test and lint commands
npm test # full offline test suite
npm run consistency # cross-artifact drift check
npx eslint . # linter
CI=true DEVTEAM_HEADLESS_COMMAND=cat npm test # full CI run (no host CLI needed)
DEVTEAM_HEADLESS_COMMAND=cat stubs the host CLI for headless tests without claude or codex installed.
Where things live
| Concern | Path |
|---|---|
| Stage definitions, tracks, role assignments | core/pipeline/stages.js |
| Routing config loader | core/config.js |
| Adapter discovery + per-(stage, role) resolution | core/router.js |
| Dispatch logic (runStage / next / merge) | core/orchestrator.js |
| Gate validator + per-stage schemas | core/gates/ |
| Guards (stoplist, security-heuristic, write-audit) | core/guards/ |
| Role briefs (single source of truth) | roles/*.md |
| Rules docs | rules/*.md |
| Task skills | skills/*/SKILL.md |
| Per-host adapters | hosts/<name>/{adapter.js, capabilities.json, install/} |
| CLI entry point | bin/devteam |
Load-bearing contracts (do not break without an ADR)
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 · 67 lines · 1,093 tokens per session scan A 4a154b00ec7a
stagecraft AGENTS.md is an instructions file published in the GitHub repository telus-labs/stagecraft (6 stars, last pushed yesterday), licensed MIT. It adds 1,093 tokens to every session, about $0.0055 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
parallel-code CLAUDE.md
Claude Code instructions for johannesjo/parallel-code, covering parallel code, stack, commands, project structure and conventions.
PokeTokenBar CLAUDE.md
Claude Code instructions for chattymin/PokeTokenBar, covering poketokenbar — claude 프로젝트 지침, 참조 문서 (필요할 때 읽는다), 기여 언어 규약 (오픈소스 대비 — english first), 릴리스 (자연어 트리거) and 확장 규약 (새 프로바이더/툴 추가 시).
semantix CLAUDE.md
Claude Code instructions for Gnosil/semantix, covering 项目规则（claude code）, 1. 改动须经用户过目；由 claude 提交到分支 + pr，用户 review 后合并 and 2. 本地实验区：论文数据与实验材料不进 github.
cc-statistics CLAUDE.md
Instructions for androidZzT/cc-statistics, covering claude.md, project, setup, usage and architecture.
intuitive-flow AGENTS.md
AGENTS.md instructions for MiaoDX/intuitive-flow, covering codex guide, environment, delegation and verification, development and testing and preferred skills and workflow routing.
SubFrame AGENTS.md
AGENTS.md instructions for Codename-11/SubFrame, covering subframe - subframe project, core working principle, relationship to native ai tools, session start and concurrent work & worktrees.