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 FlyFission/nuclear-grade-context-engineering --skill running-a-review-panelgit clone --depth 1 https://github.com/FlyFission/nuclear-grade-context-engineeringWrote 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/flyfission/nuclear-grade-context-engineering/running-a-review-panel)<a href="https://agentmods.dev/skills/flyfission/nuclear-grade-context-engineering/running-a-review-panel"><img src="https://agentmods.dev/badge/skills/flyfission/nuclear-grade-context-engineering/running-a-review-panel/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/flyfission/nuclear-grade-context-engineering/running-a-review-panel"><img src="https://agentmods.dev/badge/skills/flyfission/nuclear-grade-context-engineering/running-a-review-panel.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 | $0.00093 | $0.02689 |
| Opus 5.5 | $0.00037 | $0.01076 |
| Sonnet 5.5 | $0.00019 | $0.00538 |
| Haiku 4.5 | $0.00009 | $0.00269 |
Grade A, and why
running-a-review-panel 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 3d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Running a Review Panel
Overview
The repo already says high-consequence verdicts should use a panel, and that "a panel that shares one biased brief is not three independent views, it is one view voiced three times" (docs/02-operating-system/evaluation-integrity.md §4). It has not said how to build one. This is that procedure. Its central move is making each seat declare the axis it varies -- model family, mechanism, brief, or human judgment -- because a panel's worth is not its headcount but the number of ways it can fail differently. It also separates the panel's result from its health: a panel degraded to two correlated seats still returns a confident unanimous verdict. And nothing it says is actionable until checked against live source here -- a blocking finding is a reason to look, not an authorization to fix.
Decision contract
- Claim checked: each seat names the diversity axis it varies, distinct-axis count is recorded separately from seat count, material dissent is preserved rather than averaged, and every actionable finding carries a host-verified state.
- Artifact observed: the frozen packet, the seat roster with declared axes, each seat's independent first-pass response, any challenge-round responses, and the degradation record ->
panel.mdplus Evidence IDs inverification.md. - Decision affected: block -- does the panel's verified finding set support the underlying verdict, or does dissent or degradation escalate the call to a human?
- Failure class: false-independence (correlated seats counted as separate views, consensus treated as proof, dissent averaged away, a degraded panel reported as full, or an unverified finding acted on).
- Next action: record result and health together, verify each actionable finding against live source, and escalate a split or degraded panel rather than resolving it by vote.
When to Use
- A trust-bearing or irreversible verdict -- ship, block, apply-clearance, a security or authorization call -- rests on one reviewer.
- The work is Nuclear / Tier 0, or a Standard change whose blast radius reached a critical system.
- A clean verdict came back on work where a wrong pass is expensive and you cannot name what would have caught the miss.
- Reviewer and actor share a model family, brief, or orchestrator, and you need a check that can fail differently (
docs/02-operating-system/actor-evidence-independence.md). - A consequential plan is about to be locked in and no one has stated the strongest opposing case.
- A prior OPEX record found a review missing a defect another method would have caught.
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.
- 3d ago First seen · 126 lines · 93 tokens per session scan A 6c272203dd19
running-a-review-panel is a skill published in the GitHub repository FlyFission/nuclear-grade-context-engineering (33 stars, last pushed 3d ago), licensed MIT. It adds 93 tokens to every session and 2,689 once invoked, about $0.0004 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 2026-10-22.
Other skills, from other repositories
code-refiner
Deep code simplification and refactoring preserving behavior across Python, Go, TypeScript, Rust. Targets complexity, anti-patterns, readability debt. Triggers on: "simplify this code", "refactor for clarity", "reduce complexity", "make this more readable", "tech debt cleanup", "too much nesting".
package-optimizer
Evaluate one existing package or bounded package family from recorded evaluator evidence and a capability profile, then propose retain, simplify, strengthen, retire, or inconclusive without editing. Use when optimizing a skill, agent, hook, rule, command, utility, or preset; evaluating whether package detail is…
review-skill
Review a proposed Agent Skill for structural validity and content quality before publishing. Runs the skill-validator CLI to check for structural issues, scores the skill with an LLM judge, and interprets results to advise authors on what to address. Use when a user wants to review, validate, or quality-check an Agent…
concord-relay
Keep this Grok session reachable by other Concord agents while idle.
pre-landing-review
Gate-oriented safety audit for code changes before landing, using a checklist with two-pass severity triage. Triggers on: "is this safe to land", "pre-landing review", "safety check before merge", "gate check", "/pre-landing-review". NOT for diff review, use pr-review.
false-positive-gate
Use when you have a candidate security finding and before it goes in a comment - restate it as a crossed boundary, prove reachability, impact and a concrete exploit, apply triage dismissals, route out-of-repository facts to needs-validation, keep the effect no stronger than the trace, then the self-refute and verifier…