Borrowing it
Nothing to install: this file belongs to sponge-b0b/Polaris. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sponge-b0b/Polaris/main/.agents/skills/review-spec/SKILL.mdgit clone --depth 1 https://github.com/sponge-b0b/PolarisWrote 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/sponge-b0b/polaris/review-spec)<a href="https://agentmods.dev/skills/sponge-b0b/polaris/review-spec"><img src="https://agentmods.dev/badge/skills/sponge-b0b/polaris/review-spec/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/sponge-b0b/polaris/review-spec"><img src="https://agentmods.dev/badge/skills/sponge-b0b/polaris/review-spec.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 144 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 | $0.00034 | $0.08238 |
| Opus 5 | $0.00017 | $0.04119 |
| Sonnet 5 | $0.00007 | $0.01648 |
| Haiku 4.5 | $0.00003 | $0.00824 |
Grade A, and why
review-spec 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 4d 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 — 820 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Spec
Review the exact verified state of a completed Spec along the applicable independent axes. This SKILL.md is the single authoritative procedure for $review-spec.
The preserved procedure below remains normative. The hardening sections immediately below strengthen frozen-finding provenance, semantic scope attribution, certified review-proof reuse, certified semantic-domain finality, and the human-facing aggregate format; where those rules conflict with older wording later in this file, the hardening rules win.
Human-Facing Aggregate Format
The final user-facing review result MUST present the three review axes in this order and MUST always include both Blocking and Advisory subsections for every axis, even when a subsection has no findings:
## Standards
### Blocking
- <findings or None>
### Advisory
- <findings or None>
## Spec
### Blocking
- <findings or None>
### Advisory
- <findings or None>
## Architecture
### Blocking
- <findings or None>
### Advisory
- <findings or None>
Use None. when a subsection has no findings so the presentation shape remains stable across review runs.
Keep findings under their originating axis and severity. Do not collapse Blocking and Advisory findings into one bullet list, and do not replace this human-facing projection with Root Blocker status, coverage accounting, reviewer-execution metrics, or convergence/effectiveness statistics.
The compact coverage/effectiveness output required below remains required, but it is supplemental and MUST appear after the three-axis findings projection.
Owner-overridden, scope-retired, Root Blocker, provenance, architecture-handoff, remediation, and lifecycle information remains governed by the procedure and may follow the three-axis findings as applicable.
Preserve the Adversarial Boundary
$review-spec remains downstream of a passing independently certified $verify-spec result.
Do not:
- verify ordinary ticket closure here;
- rerun
$verify-ticket-closureor$verify-spec-closuremerely to confirm a review finding; - repair upstream verifier policy during the review;
- weaken a current in-domain finding because an earlier verifier reported PASS.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago Changed · +232 lines 4a683a0574df
- 6d ago Changed · -239 lines · -4 tokens per session 3efafb950975
- 10d ago First seen · 827 lines · 38 tokens per session scan A 0c6e862c46b1
review-spec is a skill published in the GitHub repository sponge-b0b/Polaris (4 stars, last pushed today), licensed Apache-2.0. It adds 34 tokens to every session and 8,238 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…