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 skills add synaptiai/synapti-marketplace --skill team-coordinationgit clone --depth 1 https://github.com/synaptiai/synapti-marketplaceWrote 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/skills/synaptiai/synapti-marketplace/team-coordination)<a href="https://agentmods.dev/skills/synaptiai/synapti-marketplace/team-coordination"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/team-coordination/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/skills/synaptiai/synapti-marketplace/team-coordination"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/team-coordination.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 | $0.01088 |
| Opus 5 | $0.00037 | $0.00544 |
| Sonnet 5 | $0.00015 | $0.00218 |
| Haiku 4.5 | $0.00007 | $0.00109 |
Grade A, and why
team-coordination 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team Coordination
Contract
Independent analysis before shared conclusions: teammates who see each other's findings are contaminated reviewers. Applies only when agentTeams: true and CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS is set; commands/review.md Path A applies it, using the tables in references/paired-review-protocol.md verbatim. Returns consolidated P1/P2/P3 findings, each carrying a confidence and a disposition from the controlled set consensus|validated|refined|kept|unchallenged. The only permitted skip is the documented per-facet fallback to single-reviewer Path B; a paired-protocol failure never blocks a review.
When to Spawn Teams
| Scenario | Decision |
|---|---|
| Review with 3+ facets | Spawn: independent analysis enables the adversarial protocol |
| Large feature (>5 acceptance criteria, independent modules) | Suggest: parallel implementation across modules |
| Debugging with competing hypotheses | Spawn: one hypothesis per teammate |
| Small feature (<3 criteria) or sequential dependencies | Single session |
Task Sizing
5-6 tasks per teammate, each completable without coordination and carrying its own acceptance criteria. Overlapping file sets go to the same teammate.
Adversarial Review Protocol
Each facet runs as a paired reviewer: a skeptic ("assume the diff is broken until proven otherwise") and a verifier ("assume correct; look for missed edge cases and unenforced invariants"), dispatched in parallel with no view of each other. The default 6-facet topology is 12 invocations: 5 Agent(...) pairs plus 2 Skill(holdout-validation) lens calls.
- Independent analysis. Both variants return P1/P2/P3 findings with
file:linecitations. No challenge information in this phase. - Share. The lead indexes findings by facet. No LLM call. Holdout findings are indexed for consensus matching only.
- Challenge (disposition-only). Each variant labels the other's findings
AGREE,DISAGREE: <reason>, orREFINE: priority= category=WITHOUT re-reading the diff. Holdout-validation is excluded by design: it is objective claim-verification, soDISAGREEhas no meaning there. - Synthesize. The lead applies the consolidation table mechanically: both raised independently (same facet, file, lines ±2, priority ±1) → HIGH
consensus; AGREE → HIGHvalidated; REFINE → MEDIUMrefined; DISAGREE → LOWkept; timeout/error → MEDIUMunchallenged; both DISAGREE → dropped and journaled under## Dropped after challenge. The lead never adjudicates. - Emit. Finding tables carry a trailing
_(confidence · disposition)_suffix; theFLOW_REVIEW_CYCLEmarker carries the 7-field rows perreferences/finding-ledger-parser.md.
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 Changed · -162 lines · -5 tokens per session 4e453fcf0bda
- 9d ago First seen · 219 lines · 80 tokens per session scan A b39b0384b1da
team-coordination is a skill published in the GitHub repository synaptiai/synapti-marketplace (6 stars, last pushed today), licensed Apache-2.0. It adds 75 tokens to every session and 1,088 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 2026-09-03.
Other skills, from other repositories
check
Confirm a change before merge. /check verify drives the real app to prove behavior against the spec (every acceptance criterion met, every surface built). /check review runs a senior code review on a fresh model, one that did not write the code. Verify after /develop, review before a PR. Writes to docs/reviews/, never…
independent-review-loop
Independent review loop run before delivery in code work. An independent reviewer (Codex, or fresh Codex-style subagents) reads the whole PR against the approved outcome; the lead fixes in-scope functional findings and re-reviews until none remain. Its differentiator is independence and exhaustiveness — a reviewer…
x-spec
A system-planning guide that turns a vague idea into a set of linked design documents. It defines goals, modules, interfaces, data, workflows, and ways to check the result.
x-audit-arch
A project-wide architecture review skill that checks whether code is placed in the right modules and whether important definitions have one reliable source.
x-cr
A software-correctness investigation skill for finding why code behaves differently from what was expected. It uses evidence from code paths, specifications, tests, logs, and changes to assess possible causes.
x-multi-llm-align
A review process in which two sub-agents examine an API, data format, event schema, or workflow from their separate implementation perspectives. The user passes documents and feedback between them over multiple rounds.