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 independent-review-loopgit 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/independent-review-loop)<a href="https://agentmods.dev/skills/dheerg/swarms/independent-review-loop"><img src="https://agentmods.dev/badge/skills/dheerg/swarms/independent-review-loop/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/independent-review-loop"><img src="https://agentmods.dev/badge/skills/dheerg/swarms/independent-review-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 84 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00114 | $0.08476 |
| Opus 5.5 | $0.00046 | $0.03390 |
| Sonnet 5.5 | $0.00023 | $0.01695 |
| Haiku 4.5 | $0.00011 | $0.00848 |
Grade A, and why
independent-review-loop 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.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operational spec for the team lead. This skill runs an independent review pass at delivery: a reviewer that fails differently from the author reads the whole PR against the approved outcome, the lead fixes what is in scope, and the loop repeats until the reviewer finds no more in-scope functional issues. It is the automated form of "ship, then loop the PR through Codex until it stops finding edge cases" — with the lead acting as the operator who keeps findings on-scope.
What distinguishes this from the team's own review and the recursive-refinement ladder is independence and exhaustiveness: the reviewer is a different model (Codex) or a fresh-context agent that fails differently from the authors, and it runs to exhaustion — until no in-scope functional finding remains — rather than the bounded rung ladder. (The ladder hunts bugs too, as it drives the work to the full scope of the outcome; the new axis here is the independent eye run to clean, not bug-hunting per se.) It is a distinct pass; it never replaces the ladder.
Only the lead runs this. Reviewers (Codex, or fresh subagents) are read-only; the lead is the sole writer, same as every other phase.
When this runs
Invoked from the unified pre-ship gate in code-mode's Refine/Deliver (and /swarm:refine) — the gate the lead presents once the team reaches 9/10+, offering (thoroughness-descending): recursive refinement + independent review / recursive refinement only / independent review loop only / ship as is. This skill runs for the two options that include the independent loop — recursive refinement + independent review (after the recursive ladder completes) and independent review loop only (on its own); recursive refinement only and ship as is do not invoke it. Deliver invokes this skill when the independent-review-loop pending run-state task recorded at the gate is open — it branches on that recorded task, not on recall of the pick.
It runs after the ship steps complete (PR-then-loop on the common path): when a PR was created, the loop reviews the PR's diff and pushes each round's fixes to it; on a commit-only / push-only ship with no PR, it reviews the pushed branch against its base. The diff base is resolvable from the PR when one exists (see the loop's base resolution below for the no-PR fallback).
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 · 146 lines · 114 tokens per session scan A 2582fcda2da9
independent-review-loop is a skill published in the GitHub repository DheerG/swarms (85 stars, last pushed 3mo ago), licensed MIT. It adds 114 tokens to every session and 8,476 once invoked, about $0.0005 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.