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 doordash-oss/agentic-orchestrator --skill review-commentsgit clone --depth 1 https://github.com/doordash-oss/agentic-orchestratorWrote 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/doordash-oss/agentic-orchestrator/review-comments)<a href="https://agentmods.dev/skills/doordash-oss/agentic-orchestrator/review-comments"><img src="https://agentmods.dev/badge/skills/doordash-oss/agentic-orchestrator/review-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/skills/doordash-oss/agentic-orchestrator/review-comments"><img src="https://agentmods.dev/badge/skills/doordash-oss/agentic-orchestrator/review-comments.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00033 | $0.01407 |
| Opus 5 | $0.00016 | $0.00704 |
| Sonnet 5 | $0.00007 | $0.00281 |
| Haiku 4.5 | $0.00003 | $0.00141 |
Grade A, and why
review-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 10d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review-Comments Cycle
The harness has detected unaddressed PR review comments on one or more of this feature's PRs. Your job is to address (or, with reasoning, dismiss) every aggregated comment, validate your edits with focused development tests, and emit one combined review-resolutions.json. One agent session per iteration; the same handoff contract as the implement skill applies.
Workspace
cwdis the feature state dir.--add-dirmounts everyFeature.Reposworktree — not just the repos with comments. Review threads frequently reference cross-repo behavior, and you may need to read a sibling repo's source to judge a comment correctly even when no edit lands there.- The aggregated plan at
## Handoff Contract → Plan pathlists each repo with unaddressed comments, its PR URL, and the comments themselves. Every comment carries a**Repo:** <name>tag andrepo: <name>annotation so you can route the fix. - Agentico does not guess language-specific project commands for this plan-less cycle. Use focused development tests appropriate to the edits.
Per-repo dispatch
Per-repo edits are delegated by prompt, not by cwd. Each Task sub-agent's prompt names exactly one repo and constrains file edits to that repo's worktree. Today's main-vs-sub split is preserved:
- Stays in main: plan reading, deciding address/dismiss for each comment, sequencing across repos, reading the testing contract, emitting the handoff, writing the combined
review-resolutions.json. - Delegated to per-repo Task agents: the actual code edits, focused development tests, commit + push.
The Process
Step 1 — Read the aggregated plan
The plan has one section per repo with unaddressed comments. For each comment, decide:
- Addressed — the feedback warrants a code change. Make the change in the named repo.
- Dismissed — the comment is already handled, not applicable, or the current approach is better. Document the reasoning in the resolution entry.
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.
- 10d ago First seen · 94 lines · 33 tokens per session scan A cab502f3cdf2
review-comments is a skill published in the GitHub repository doordash-oss/agentic-orchestrator (103 stars, last pushed yesterday), licensed Apache-2.0. It adds 33 tokens to every session and 1,407 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 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
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.
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…