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 archcore-ai/plugin --skill reviewgit clone --depth 1 https://github.com/archcore-ai/pluginWrote 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/archcore-ai/plugin/review)<a href="https://agentmods.dev/skills/archcore-ai/plugin/review"><img src="https://agentmods.dev/badge/skills/archcore-ai/plugin/review/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/archcore-ai/plugin/review"><img src="https://agentmods.dev/badge/skills/archcore-ai/plugin/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 48 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00127 | $0.02523 |
| Opus 5.5 | $0.00051 | $0.01009 |
| Sonnet 5.5 | $0.00025 | $0.00505 |
| Haiku 4.5 | $0.00013 | $0.00252 |
Grade A, and why
review 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 29d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/archcore:review
Review the changes on the current branch against the .archcore/ knowledge base, in both directions: whether the changed code still matches the documents that claim it, and whether the changed documents still match the code they describe. On the default branch, or with an empty diff, the skill reports project health instead. Write affinity: experience types — cpat and task-type land through the experience track. This is also the only skill that removes a document: closeout.discharge removes a completed plan, and actualize.fix may remove a long-stale draft of any type — both via mcp__archcore__remove_document, each under its own confirmation.
Command tense: /archcore:plan declares a future canon delta, /archcore:document
records the present state — including work that shipped without a plan — and
/archcore:review reconciles a past declared delta. Δ vocabulary:
skills/_shared/delta-routing.md.
When to use
- "Review my branch" / "Review the changes before merge" → branch review
- "Show status" / "How many docs do we have?" → project health dashboard
- "Are any docs out of date?" / "Check if documentation matches the code" →
drift - "Audit the knowledge base" / "Documentation gaps?" →
deep - Session-start staleness warning appeared →
drift - "Close out the feature" / "Ship the feature and close it out" →
closeout - "Capture this repeated change as a pattern" →
experience
Not review:
- Documenting a module, decision, or topic →
/archcore:document - Planning a feature or initiative →
/archcore:plan - First-time setup →
/archcore:init
Routing table
| Signal | Route |
|---|---|
| No arguments, branch with changes | → branch review, steps 1–4 |
| On the default branch, or empty diff | → project health dashboard (step 1 fallback) |
First word drift |
→ actualize track (step 3); scope from step 1 when the branch boundary resolves, all documents on on-default-branch or empty-diff |
First word deep |
→ actualize track over all documents, plus coverage and relation findings |
First word closeout |
→ closeout track (skills/_shared/tracks/closeout.md), scope pre-filled from the step 1 branch-state block; exits into the step 4 experience offer |
First word experience |
→ experience track (skills/_shared/tracks/experience.md) over the branch scope; the detect gate selects cpat or task-type |
| Path, tag, or scope argument | → the named scope narrows or replaces the branch scope |
| Completion signals: "close out the feature", "ship the feature and close it out" — an explicit completion or acceptance verb, not mere branch readiness. A plain "review my branch" stays on branch review even for a merge-ready branch | → closeout track (skills/_shared/tracks/closeout.md), scope pre-filled from the step 1 branch-state block; exits into the step 4 experience offer |
Any other first word — a track or type name such as actualize or cpat, or a former flag such as --drift |
→ topic text; route by the signals above |
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.
- 29d ago Changed · +4 lines · +20 tokens per session 5170bfc330f5
- 1mo ago Changed · +7 lines 76b60b485c9e
- 1mo ago First seen · 109 lines · 107 tokens per session scan A 151d13e30374
review is a skill published in the GitHub repository archcore-ai/plugin (58 stars, last pushed 26d ago), licensed Apache-2.0. It adds 127 tokens to every session and 2,523 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
pr
Comprehensive PR/issue review - analyzes architecture, tests, identifies unrelated changes mixed in, drafts review comment or issue comment. Use when user asks to review a PR, check a PR, look at PR changes, or comment on an issue.
explain
Guided code tour of a file or subsystem this session touched — entry point, the load-bearing pieces, the edges, and what connects to it.
dev
Implement from a spec or plan: extract stories, build in safe waves, test, commit, and get peer review per story. Use for "implement", "build/code this plan", or targeted fix findings. If no plan exists, use /ship:design first.
refactor
Improve existing code without changing behavior: scan smells, simplify, dedupe, reuse utilities, and verify after edits. Use for refactor, cleanup, simplify, reduce duplication, extract method, dead code, or code smells. No PR.
review
Static code review of the active diff: trace changed paths and report concrete P1/P2/P3 correctness, security, or spec bugs with file:line evidence. Use for code review or bug checks. Not runtime QA.
pn-best-of-n
Run 2–3 competing implementations of the same spec in isolated worktrees, eliminate failures via objective gates, then judge survivors with a separate premium-tier pass. Use for ambiguous algorithm/API/refactor choices with strong tests — not auth/security paths.