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.
git clone --depth 1 https://github.com/yonatangross/orchestkitWrote 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/commands/yonatangross/orchestkit/review-artifact-comments)<a href="https://agentmods.dev/commands/yonatangross/orchestkit/review-artifact-comments"><img src="https://agentmods.dev/badge/commands/yonatangross/orchestkit/review-artifact-comments/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/commands/yonatangross/orchestkit/review-artifact-comments"><img src="https://agentmods.dev/badge/commands/yonatangross/orchestkit/review-artifact-comments.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 | $0.00082 | $0.00741 |
| Opus 5.5 | $0.00033 | $0.00296 |
| Sonnet 5.5 | $0.00016 | $0.00148 |
| Haiku 4.5 | $0.00008 | $0.00074 |
Grade A, and why
review-artifact-comments 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 today.
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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto-generated from skills/review-artifact-comments/SKILL.md
Source: https://github.com/yonatangross/orchestkit
review-artifact-comments
Comments live inside the artifact, in the block at its end (format: the create-plan skill's
references/artifact-layout.md). A reviewer adds one with the script or types it into the block by
hand; both are read the same way. Nothing here deletes a comment.
Steps
-
Pick the artifact. Use the file given. Otherwise list the task directory and ask which one:
node "skills/review-artifact-comments/scripts/artifact.mjs" status --task-dir .ork/tasks/<task> -
Read the artifact in full, then its open comments:
node "skills/review-artifact-comments/scripts/artifact.mjs" list --file <artifact> --open -
Ask how to proceed unless the user already said (AskUserQuestion), for example:
- revise the artifact from the comments (hand off to
/ork:iterate-planor/ork:iterate-research) - revise and resolve the comments it settles
- investigate the comments and reply with findings, no revision
- revise the artifact from the comments (hand off to
-
Work one comment at a time. Check the claim in the code before answering. Reply with what you found or changed:
node "skills/review-artifact-comments/scripts/artifact.mjs" reply --file <artifact> --id c1 --author Claude --text "..." node "skills/review-artifact-comments/scripts/artifact.mjs" resolve --file <artifact> --id c1 --author Claude --text "..."Resolve only when told to, or when the reply records a fix already made.
-
Approve only for the reviewer, never for the author. The approver is the reviewing seat, and
--refnames the LAND message or comment id the approval rests on. The script refuses while a comment is open or when--byis the artifact'sauthor(exit 1), and without--byor--ref(exit 2):node "skills/review-artifact-comments/scripts/artifact.mjs" approve --file <artifact> --by <reviewer seat> --ref <LAND or comment id>
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.
- today First seen · 68 lines · 82 tokens per session scan A b2ae2a452e4e
review-artifact-comments is a command published in the GitHub repository yonatangross/orchestkit (298 stars, last pushed today), licensed MIT. It adds 82 tokens to every session and 741 once invoked, about $0.0003 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 2026-10-27.
Other commands, from other repositories
gc
On-demand code-drift / entropy scan (garbage collection) via a fresh-context drift-analyst subagent. Checks changed/active code against golden-rules.md + generic drift heuristics (dead code, duplication, doc-drift) and reports findings with an evidence path. Read-only — recommends, never auto-refactors. Not git gc.
pn-audit-api
Surgical API design review — REST conventions, status codes, response shapes, validation, and schema leaks. Use standalone or as part of pn-backend-audit. Outputs a scored fix roadmap.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.