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 DheerG/swarms --skill resolve-disputegit clone --depth 1 https://github.com/DheerG/swarmsWrote 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/dheerg/swarms/resolve-dispute)<a href="https://agentmods.dev/skills/dheerg/swarms/resolve-dispute"><img src="https://agentmods.dev/badge/skills/dheerg/swarms/resolve-dispute/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/dheerg/swarms/resolve-dispute"><img src="https://agentmods.dev/badge/skills/dheerg/swarms/resolve-dispute.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 | $0.00032 | $0.00372 |
| Opus 5.5 | $0.00013 | $0.00149 |
| Sonnet 5.5 | $0.00006 | $0.00074 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
resolve-dispute 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 1mo 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
A review finding is stuck. Structure its resolution in three steps.
Step 1 — Frame the dispute. Identify and state aloud:
- The disputed finding (one sentence)
- Who holds it
- The facilitator's prior arbitration ruling (one sentence)
Step 2 — Send the reviewer this message, substituting [finding] with the actual finding:
Your finding — [finding] — was arbitrated. To keep it open, you must provide ONE of: (a) A concrete failure scenario: specific inputs or conditions that produce wrong behavior (b) A source citation: file, line number, and what it shows (c) A direct counterexample to the arbitration reasoning
One response. No response counts as concession. After that, the facilitator rules and the finding is DECIDED.
Step 3 — Rule and tag.
After the reviewer responds:
- Evidence present → the facilitator evaluates it on the merits and rules. Tag the finding DECIDED regardless of outcome.
- No evidence → the facilitator tags DECIDED, asks the reviewer to re-score.
- No response → the facilitator tags DECIDED.
DECIDED findings cannot be re-raised without new substance. This enforces the existing "Don't regurgitate decided points" rule.
What this skill must not do:
- Override a finding backed by real evidence
- Auto-resolve — the facilitator still decides after hearing the evidence
- Apply to first-round disagreements — use normal arbitration first
- Suppress legitimate concerns — evidence always reopens the door
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.
- 1mo ago First seen · 39 lines · 32 tokens per session scan A fb6c2cb48726
resolve-dispute is a skill published in the GitHub repository DheerG/swarms (85 stars, last pushed 3mo ago), licensed MIT. It adds 32 tokens to every session and 372 once invoked, about $0.0001 per session on Opus 5.5. 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 skills, from other repositories
pocket-development
Execute Pocket implementation plans through bounded packets, delegated implementation, independent review, and phase handoff. Use when the user asks to execute a plan or dispatch its tasks.
pocket-grinding
BDD-driven feature/fix discovery before any implementation. Use when planning a feature, designing a fix, or exploring options before building. Trigger on "pocket-grinding", "brainstorm", "think through", "plan this", "before we build". Invokes pocket-planning at handoff.
pocket-planning
Converts a pocket-grinding spec into a TDD-structured execution plan of full Pocket Packets. Use when pocket-grinding handoff arrives (spec path + acceptance criteria). Trigger on "create plan", "build plan", "pocket-planning", or when pocket-grinding skill invokes this. Outputs tasks ready to dispatch via…
pocket-closing
Close a reviewed Pocket phase or plan when the user explicitly requests closeout, including as part of an end-to-end request. Reconcile verdicts with log.json, advance only a passing phase, append a readable per-phase closeout, and finalize the plan when all phases are done. A passing verdict alone does not authorize…
validate-plan
Validate implementation plans against DRY, YAGNI, TDD principles and best practices. Use when reviewing plans from pocket-planning or another planning workflow to identify gaps, anti-patterns, and improvement opportunities before execution.
create-pr
User-triggered Enterprise PR recorder for a completed phase. Stacked plans publish their phase branch through the publish-phase repair command; other plans create or reuse the current-branch PR. Links the tracked issue and records PR identity. It never posts review verdicts, never rebases, and never force-pushes.