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/steward-fi/steward/agents-mdgit clone --depth 1 https://github.com/Steward-Fi/stewardWrote 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/steward-fi/steward/agents-md)<a href="https://agentmods.dev/instructions/steward-fi/steward/agents-md"><img src="https://agentmods.dev/badge/instructions/steward-fi/steward/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 | $0.00428 | $0.00428 |
| Opus 5 | $0.00214 | $0.00214 |
| Sonnet 5 | $0.00086 | $0.00086 |
| Haiku 4.5 | $0.00043 | $0.00043 |
Grade A, and why
steward 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.
Repository operating guide
Setup
- Use Bun 1.3 or newer and install dependencies with
bun install --frozen-lockfile. - Target
develop. Refreshorigin/developbefore final review, and preserve unrelated changes in shared or dirty worktrees. - Keep secrets in ignored environment files. Start from
.env.example; never commit real keys, tokens, passwords, recovery material, or production identifiers.
Validation
- Run the smallest relevant package tests while iterating, then run
bun run lint,bun run typecheck, and the affected test suites. bun run verifyis the deterministic root validation contract. API and proxy E2E commands require the services provisioned in CI; browser suites underweb/e2euse their own Playwright command.- Treat a result as current only when it ran against the exact commit being reviewed. Rerun affected checks after rebases, conflict resolution, generated-file updates, or fixups.
- Report local validation, merge state, deployment, and external verification separately.
Generated files
- Run
bun scripts/generate-openapi.tsto refreshdocs/openapi.jsonanddocs/api-reference/openapi.jsonfrom the runtime contract. - Run
cd packages/api && bun run openapito refresh both OpenAPI documents and generated SDK API types. Commit every generated output with its source change. - Do not hand-edit lockfiles or generated API outputs; use the owning generator or package manager.
Database migrations
- Add immutable numbered SQL migrations under
packages/db/drizzle/and register them inpackages/db/drizzle/meta/_journal.jsonthrough the repository migration workflow. - Never rewrite an applied migration or add an unnumbered duplicate. Use a new migration for follow-up schema changes.
Documentation and comments
- Describe current behavior and trust boundaries. Keep change history, PR rationale, and superseded plans in Git history or a clearly historical archive.
- Keep README files, deployment instructions, package manifests, generated contracts, and examples synchronized with the code. Verify relative links when moving documentation.
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 · 428 tokens per session scan A 272859d604ac
steward AGENTS.md is an instructions file published in the GitHub repository Steward-Fi/steward (95 stars, last pushed 9d ago), licensed MIT. It adds 428 tokens to every session, about $0.0021 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
AUTHENSOR AGENTS.md
Instructions for AUTHENSOR/AUTHENSOR, covering agents.md — authensor integration guide for ai agents, what authensor does for you, quick integration, if you have access to http and if you have access to npm / npx.
AUTHENSOR CLAUDE.md
Instructions for AUTHENSOR/AUTHENSOR, covering authensor — claude code project context, what is this project, repository structure, key technical conventions and development commands.
reins AGENTS.md
Instructions for WellDunDun/reins, covering agents.md, repository overview, product model (must keep clear), architecture and documentation map.
reins CLAUDE.md
Instructions for WellDunDun/reins: Canonical project instructions live in AGENTS.md.
openscreen AGENTS.md
AGENTS.md instructions for getopenscreen/openscreen, covering agents.md, setup commands, development principles, project layout and code style.
openstatus AGENTS.md
AGENTS.md instructions for openstatusHQ/openstatus, covering agents.md, verify your change, toolchain, architecture and tests.