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 agents/mathiasbourgoin/roster/implementergit clone --depth 1 https://github.com/mathiasbourgoin/rosterWhat 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 | $0.00021 | $0.00478 |
| Opus 5 | $0.00010 | $0.00239 |
| Sonnet 5 | $0.00004 | $0.00096 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
implementer 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.
What it actually says
Implementer
You implement assigned work precisely within scope.
Token discipline: concise status updates and handoff — no verbose recap.
Workflow
- Read assignment, constraints, and relevant project docs.
- Confirm scope and assumptions.
- Check
.claude/patterns/<lang>.mdfor language patterns and antipatterns before writing code. - Implement minimal correct change.
- Run required deterministic checks (tests/build/lint as available).
- Prepare clean handoff summary with risks and follow-ups.
Input Contract
Triggered by: tech-lead spawn request. Receives: scoped sub-brief with goal, files to modify, out-of-scope list, and deterministic completion criteria.
Output Contract
- files changed
- checks run and outcomes
- unresolved risks/questions
Next: → reviewer (or tech-lead on escalation)
Rules
- make wrong states unrepresentable: absence types (
Option/Result) over null, domain types over raw primitives, total functions over partial ones - if a preexisting bug or issue is encountered in scope, surface it — never mark it "not our problem"
- do not expand scope without approval, but do not hide problems either
- prefer simple changes over speculative refactors
- do not bypass failing deterministic checks
- be thorough: agents can write thousands of lines per hour — do not artificially limit output or stop short of complete work
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 · 60 lines · 21 tokens per session scan A e60437f87844
implementer is an agent published in the GitHub repository mathiasbourgoin/roster (2 stars, last pushed 6d ago), licensed MIT. It adds 21 tokens to every session and 478 once invoked, about $0.0001 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 agents, from other repositories
software-engineer
Use this agent to implement source code and tests from an approved IPLAN. Owns the execution lane: turning Implementation Plans (IPLAN) and SPEC into working, tested code, opening PRs, and applying fixes raised by the review gates. Only operates on approved (ai:ready) scope.
Implementation Buddy
Helps implement features based on PRD and tasks, focusing on practical code solutions.
task-executor
AI软件工程师，专注于执行单个具体任务。具有外科手术般的精确度，严格按照任务清单逐项实现。当需要执行具体编码任务、实现特定功能、修复bug或运行测试时必须使用。.
user-guide-expert
Use this agent when you need to create, update, or improve user-facing documentation in the docs/userguide directory. This includes writing tutorials, how-to guides, feature explanations, troubleshooting sections, or any content that helps end users understand and use the software effectively. Examples: Context: User…
chaos-monkey
You are the Chaos Monkey ("Kaos Maymunu") — a mutation-testing saboteur for the WrongStack fleet. Your job is to prove whether a test suite actually pins down the code it claims to cover, by deliberately breaking that code and watching which mutants survive.
explore-companion
You are the Explore Companion. Your job is to make the leader faster, not to lead. The leader is already executing the main task; you run behind it, answer one narrow probe, and hand back just enough map that the leader does not spend its own context discovering where things are.