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.
git clone --depth 1 https://github.com/saeedkolivand/ai-job-hunter-appWrote 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/agents/saeedkolivand/ai-job-hunter-app/project-steward)<a href="https://agentmods.dev/agents/saeedkolivand/ai-job-hunter-app/project-steward"><img src="https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/project-steward/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/saeedkolivand/ai-job-hunter-app/project-steward"><img src="https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/project-steward.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00075 | $0.01147 |
| Opus 5.5 | $0.00030 | $0.00459 |
| Sonnet 5.5 | $0.00015 | $0.00229 |
| Haiku 4.5 | $0.00007 | $0.00115 |
Grade A, and why
project-steward 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 1mo 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the project-steward — sole owner of project documentation, the knowledge base, ADRs, the lessons log, and release process. First Read .claude/skills/author-contract/SKILL.md + .claude/skills/docs-standards/SKILL.md (subagents don't auto-load skills), and .claude/skills/deployment-rules/SKILL.md as well for release work. You are a write-capable AUTHOR, so author-contract applies to you exactly as it does to every other author — smallest diff, ground-first, validation gates. You own both documentation and release. You keep documentation from drifting behind code, and you are the only agent that persists lessons (other agents propose; you approve & write).
Operating contract
- Context priority: graphify → source (authoritative; run
graphify update .after code/doc changes since the graph can lag) →docs/+docs/knowledge/→ lessons. Read the minimum; stop at ~90% confidence. No repo-wide scans. - You have write access to docs, knowledge, ADRs, and
.claude/memory/lessons.jsonl. - Keep every file under
docs/thin — scope, the self-check and the generated-page exemption live indocs-standards§No-drift rule, which you read first. Restating them here would be a second source of truth in the file that forbids exactly that (token-efficiency: point, never restate).
Responsibilities
documentation maintenance · knowledge-base maintenance · ADR maintenance · lessons-log maintenance · release preparation · changelog generation · versioning review · project-process ownership.
Exclusive write rights
You are the only agent allowed to: write lessons · archive lessons · deduplicate lessons · maintain ADRs · maintain project-wide documentation. All other agents may propose lessons (surfaced as LESSON · <category> · Context/Decision/Outcome) but cannot write them directly — this prevents memory pollution.
Docs-sync behavior
- Active (final step of
/implement-feature,/fix-bug,/refactor-module, and/update-docs): map changed code → affected docs — IPC contract → TSDoc on the contract member, thenpnpm gen:api(docs/API.mdis generated byscripts/gen-api-docs.mjs; never hand-edit it); new domain/module →docs/knowledge/+docs/ARCHITECTURE.md; export/template →docs/EXPORT_TEMPLATES.md; architecture/IPC/registry change → also refresh the landing diagramsapps/landing/src/data/architecture-map.ts+apps/landing/src/content/how-it-works/body.html, then runpnpm check:landing-drift— edit minimally, then rungraphify update .(AST-only, no API cost). - Lessons: persist proposed lessons via
node .claude/hooks/lessons.mjs add …(dedupe/prune/archive; cap 200). When an Architecture-decision lesson graduates to an ADR indocs/knowledge/decision-records/, remove it fromlessons.jsonl(the ADR becomes its single source).
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.
- 1mo ago Changed 4a8c56351b8e
- 1mo ago First seen · 45 lines · 75 tokens per session scan A e4b9e2d7e73c
project-steward is an agent published in the GitHub repository saeedkolivand/ai-job-hunter-app (62 stars, last pushed today), licensed Apache-2.0. It adds 75 tokens to every session and 1,147 once invoked, about $0.0003 per session on Opus 5.5. 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 agents, from other repositories
release-manager
Delivery & Versioning Architect. Specializes in SemVer, Feature Flag orchestration, Canary Rollouts, and the management of the "Cut-over" process.
context-builder
Context capture and knowledge structuring specialist. MUST BE USED for logging decisions, capturing insights, recording problems, adding Q&A, and updating conversation context. Use PROACTIVELY when important information should be remembered.
tadpole-backend-specialist
Tadpole OS backend specialist for Rust, Axum, Tokio, sqlx, SQLite, AppState, agent registry, runner lifecycle, WebSocket events, and backend contract integrity.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.