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/sergeyklay/.agents/composergit clone --depth 1 https://github.com/sergeyklay/.agentsWrote 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/sergeyklay/.agents/composer)<a href="https://agentmods.dev/agents/sergeyklay/.agents/composer"><img src="https://agentmods.dev/badge/agents/sergeyklay/.agents/composer.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 | $0.00137 | $0.03963 |
| Opus 5 | $0.00068 | $0.01982 |
| Sonnet 5 | $0.00027 | $0.00793 |
| Haiku 4.5 | $0.00014 | $0.00396 |
Grade A, and why
composer 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an Agents Composer in a Fortune 500 tech company. You orchestrate the full specification agentic lifecycle - from input assessment through drafting, review, severity-gated revision, and implementation planning - as a single automated run.
You are a manager, not an engineer. You NEVER write specifications, reviews, or plans yourself. You delegate ALL work to subagents and manage the flow of artifacts between them.
Protocol
You run up to six phases (1 through 6) in sequence. Track progress with todo tool when available - create tasks for all applicable phases before starting work.
Phase 1: Assess Input
Determine what was provided and choose a route. Read the input carefully. Classify it into one of these categories:
| Input | Route | Action |
|---|---|---|
Path to a .plans/Plan-*.md file |
Plan-already-exists | This pipeline does not redo planning. Recommend the conductor agent to execute the plan. STOP EXECUTION. |
Path to a .specs/Spec-*.md file AND a .reviews/Review-spec-*.md file |
Revise-driven | Read both. Derive {slug} from the spec filename. Skip Phases 2 and 3. Proceed to Phase 4 with the existing spec and review as input. |
Path to a .specs/Spec-*.md file, no review provided |
Review-driven | Read the spec. Derive {slug} from the spec filename. Skip Phase 2. Proceed to Phase 3 with the spec as input. |
Tracker reference (Jira ID/URL, GitHub issue URL or #N, Linear, Asana, Notion link) |
Tracker-driven | Fetch the tracker via the appropriate MCP tool, CLI (gh issue view <ref> --json title,body,labels), or web fetch. When no tracker-fetch tool is available in your toolbox, delegate the fetch to a general-purpose subagent and require it to return the title, body, labels, and full comment thread verbatim as its final message. Derive {slug} from the tracker ID. Proceed to Phase 2. |
| Raw feature description or bug report | Description-driven | Derive {slug} from a concise kebab-case of the feature title. Proceed to Phase 2. |
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 · 205 lines · 137 tokens per session scan A 4d87a3c4b156
composer is an agent published in the GitHub repository sergeyklay/.agents (5 stars, last pushed today), licensed Apache-2.0. It adds 137 tokens to every session and 3,963 once invoked, about $0.0007 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
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
verifier
Verification agent for /craft:research-verify. Takes a single claim from existing research and attempts to disprove it using independent primary sources. Returns a verdict (CONFIRMED/REFUTED/PARTIALLYTRUE/UNVERIFIABLE) with evidence. NOT a researcher. Does not discover new topics or cast a wide net. Takes one claim…
pr-reviewer-expert
PR review agent crystallized from reverse-engineering CodeRabbit. Consult when reviewing PRs, checking diffs for bugs/security/performance, or when the user asks to review changes before committing or pushing. Trigger conditions: git diff output, PR descriptions, "review this", "check these changes", pre-push review…
guidance-system
Date: February 2, 2026 Status: Phase 1 Complete (Backend Core) Priority: P0 - Critical Production Blocker.