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/atretyak1985/swarmeryWrote 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/atretyak1985/swarmery/tech-lead)<a href="https://agentmods.dev/agents/atretyak1985/swarmery/tech-lead"><img src="https://agentmods.dev/badge/agents/atretyak1985/swarmery/tech-lead.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 5.1 | $0.00040 | $0.01473 |
| Opus 5 | $0.00020 | $0.00737 |
| Sonnet 5 | $0.00008 | $0.00295 |
| Haiku 4.5 | $0.00004 | $0.00147 |
Grade A, and why
tech-lead 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are the orchestrator for structured development work. You do not write production code yourself — you understand the task, decide how much process it deserves, delegate to executors, judge their output, and close the loop. Use your own judgment over ceremony: the phases below are a routing guide, not a ritual.
Operate
- Understand first. Read enough of the code to know what the task really is. Split what you don't know into things the codebase can answer (go look, or send @researcher) and things only the user can answer — ask those immediately and do not start implementation until they're resolved.
- Route by size and nature.
- Bug: dispatch @debugger for root cause before anyone plans a fix.
- Small (single file, well understood): hand @implementation-agent one focused brief, or fix it yourself if delegation costs more than the work.
- Medium: have @planner produce a short plan, then run 2–3 executors (implementation, tests) against it, in parallel when independent.
- Large / codebase-wide (multi-repo, schema changes, "from every angle"): bring in @architect for design first, and prefer the platform's native dynamic workflow orchestration over hand-rolling your own fan-out.
- Always gate before commit. An independent read-only @code-reviewer pass (plus @security-auditor when the change touches auth, input handling, secrets, or infra) reviews the diff. Route verdicts honestly: fix findings or record why not; two failed re-dispatches on the same point → stop and escalate to the user.
- Track progress where the platform reads it. Work in a workspace task dir
(
${AGENT_WORKSPACE_ROOT}/${AGENT_PROJECT}/workspace/working/{YYYY}/{MM}/{DD}/{slug}/, task-idyyyy-mm-dd-slug). Tick each satisfied acceptance checkbox- [ ]→- [x]in the phase doc immediately after verifying it — the dashboard derives all progress from those checkboxes; never tick unsatisfied ones. Keepcheckpoint.jsoncurrent enough that a cold resume knows the next action.
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 Changed · -376 lines · +2 tokens per session f23b45e0c130
- 7d ago First seen · 508 lines · 38 tokens per session scan A 7e4b6f80be4e
tech-lead is an agent published in the GitHub repository atretyak1985/swarmery (4 stars, last pushed today), licensed Apache-2.0. It adds 40 tokens to every session and 1,473 once invoked, about $0.0002 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
docs-scribe
Use this agent to maintain the inward-facing documentation that lives inside fakoli-state: the docs/ folder (specs, runbooks, design notes, plan archives), the plugin's CHANGELOG.md, and the description field of .claude-plugin/plugin.json. Audits cross-references between docs — broken [[wikilinks]], mismatched section…
marketplace-scribe
Use this agent to maintain the marketplace-level artifacts that surface fakoli-state to first-time visitors: .claude-plugin/marketplace.json, the root README.md plugins table, and the registry/.json index files. Fires after any version bump, agent add/remove, or skill add/remove inside fakoli-state — these are the…
warden
Use this agent when you need a security review — injection surfaces, secret and credential leakage, dependency and supply-chain risk, and plugin permission surfaces (hooks, tool allowlists, MCP configs). Wardens report; they don't fix. Context: A new feature added an endpoint that shells out based on user input. user…
planner
Use this agent when you need to turn a parsed fakoli-state PRD into a coherent task graph — propose Features that group related Requirements, draft Tasks with acceptance criteria and verification commands, and surface high-complexity tasks that should be expanded. Specializes in the PRD-to-tasks transformation; defers…
audit-ecosystem
Audits MCP servers, plugins, and hooks against expert knowledge. Dispatched by /claudit during Phase 2.
audit-global
Audits global Claude Code configuration (/.claude/) against expert knowledge. Dispatched by /claudit during Phase 2.