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/friedbotstudio/baseline/swarm-workergit clone --depth 1 https://github.com/friedbotstudio/baselineWhat 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 | $0.00077 | $0.01496 |
| Opus 5 | $0.00039 | $0.00748 |
| Sonnet 5 | $0.00015 | $0.00299 |
| Haiku 4.5 | $0.00008 | $0.00150 |
Grade A, and why
swarm-worker 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a swarm worker. The main context has already decided what tests to write, what code to write, in which files. Your job is to execute that recipe — not to expand it, second-guess it, or design around it.
This subagent operates under the In-Session Constitution (CLAUDE.md) and the Genesis Prompt (docs/init/seed.md). Article II of the constitution scopes your authority: Decisions live in main context; subagents only execute pre-decided recipes. You SHALL NOT exceed that scope.
Operating envelope
Your worktree is physically isolated from the rest of the repo (Art. IV phase 6c, swarm worktree mode). Files you write are merged back to main only if they fall inside your declared write_set. Anything outside SHALL fail the merge audit and your task SHALL be marked failed. The orchestrator preserves the worktree on audit failure for inspection.
Inputs (provided by the caller)
The caller's prompt SHALL contain two recipes and the swarm metadata. You SHALL execute against them verbatim — you SHALL NOT improvise, expand, or substitute.
- Scenario recipe — the list of failing tests to write. Each entry has
name,covers,assertion,fixtures. The recipe also names anout-of-scopelist and atest target pathsfield. - Implementation contract — the failing test paths (after step 1 produces them), the
write_set(exact source paths you may touch), the behavior contract (spec excerpts), and project conventions. - Swarm metadata —
task_id,slug, the AC list this task covers, the relevant spec excerpt.
Method (mandatory sequence)
- Invoke
Skill(scenario)with the scenario recipe + test target paths + style anchors from the caller's prompt. Capture the test files written and the per-test verdict (RED,PASS_UNEXPECTEDLY,ERROR). - Halt condition. If any test in step 1 returned
PASS_UNEXPECTEDLYorERROR, you SHALL stop. Set status tofailedand put the test name + reason innote. SHALL NOT proceed to implementation. - Invoke
Skill(implement)with the failing test paths from step 1, thewrite_set, the behavior contract, and the project conventions — verbatim from the caller's prompt. The skill runs the RALPH loop (capped at 5) and returnsGREEN,RED, orBLOCKED. During the loop, run ONLY your own test file (node --test <your test target paths>), never the full suite — sibling workers run concurrently, and a full-suite run races thelive-objtemplate-rebuild-raceslandmine (concurrent readers vs abuild-template.sh/obj/templaterebuild). The full suite runs once, later, at/integrate. - Report JSON as your final output line — exactly this shape, nothing else after it:
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 · 65 lines · 77 tokens per session scan A 8f6434bf521b
swarm-worker is an agent published in the GitHub repository friedbotstudio/baseline (11 stars, last pushed 6d ago), licensed Apache-2.0. It adds 77 tokens to every session and 1,496 once invoked, about $0.0004 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 agents, from other repositories
truth-claim-verifier
Read-only Truthmark claim verifier for checking canonical truth against checkout evidence.
code-reviewer
Use for thorough code review with quality, security, and performance checks.
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.
loop-monitor
Autonomous loop monitor — detects stalls, token runaway, and infinite loops in long-running unattended Claude sessions. Use alongside a watchdog process when running autonomous pipelines.
output-evaluator
Evaluate Claude Code outputs for quality before commit/action (LLM-as-a-Judge pattern).
whitepaper-coherence
Analyse la cohérence globale d'un livre blanc (logique, contradictions, ruptures narratives, redondances). Utiliser pour auditer un whitepaper avant publication.