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 agentmods add skills/jarroslav/agentic-os/code-reviewnpx skills add Jarroslav/agentic-os --skill code-reviewgit clone --depth 1 https://github.com/Jarroslav/agentic-osWhat 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 | $0.00149 | $0.02619 |
| Opus 5 | $0.00075 | $0.01309 |
| Sonnet 5 | $0.00030 | $0.00524 |
| Haiku 4.5 | $0.00015 | $0.00262 |
Grade A, and why
code-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 2d 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
code-review
On-demand, git-native code review for a working copy. You resolve a scope, write the diff to a file, invoke the downstream orchestrator inline, then read back and render its verdict. You do three things and nothing more:
Prepare context → Invoke orchestrator → Present verdict.
All the actual review reasoning — the blind, edge-case, and acceptance
lenses, standards/security adjudication, finding triage, and the machine verdict —
lives in the code-review-orchestrator skill. You do not reason about the code
yourself and you do not duplicate lens logic. Reuse the orchestrator's folded
lens definitions at ../code-review-orchestrator/references/review-lenses.md;
do not restate or diverge from them.
Blast radius
R0 — read-only. You compute diffs and write run artifacts under a run directory.
You never modify tracked source and never apply a fix the orchestrator recommends.
Relationship to the pipeline
Managed SDLC entry flows (sdlc-guided, sdlc-auto, sdlc-brief,
sdlc-engine) route the review gate through gate-arbiter, which records the
verdict to a gate ledger and may escalate. This skill is the standalone
front-door: it calls code-review-orchestrator directly, bypassing
gate-arbiter entirely — no gate ledger, no escalation.
Two shared gate-arbiter gate ids exist for this review; keep both verbatim:
| Gate id | Round | Used by this skill? |
|---|---|---|
code-review.final |
First/final review of the complete change | Yes — this is the gate you invoke under |
code-review.check |
Follow-up check round re-scoring prior findings | No — pipeline check-rounds only |
Because you only ever run code-review.final, the verdict carries no
finding_status field, and you never pass prior_verdict or memory_brief.
Inputs
| Input | Required | Meaning |
|---|---|---|
target |
optional | Scope in the user's words: a range, a named scope, and/or paths |
spec |
optional | Path to an acceptance-criteria / story doc for business review |
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.
- 2d ago First seen · 241 lines · 149 tokens per session scan A 5515a374276b
code-review is a skill published in the GitHub repository Jarroslav/agentic-os (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 149 tokens to every session and 2,619 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…