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 anantjain-xyz/symphony-rust --skill pr-feedbackgit clone --depth 1 https://github.com/anantjain-xyz/symphony-rustWrote 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/anantjain-xyz/symphony-rust/pr-feedback)<a href="https://agentmods.dev/skills/anantjain-xyz/symphony-rust/pr-feedback"><img src="https://agentmods.dev/badge/skills/anantjain-xyz/symphony-rust/pr-feedback/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/anantjain-xyz/symphony-rust/pr-feedback"><img src="https://agentmods.dev/badge/skills/anantjain-xyz/symphony-rust/pr-feedback.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 | $0.00057 | $0.00723 |
| Opus 5 | $0.00028 | $0.00362 |
| Sonnet 5 | $0.00011 | $0.00145 |
| Haiku 4.5 | $0.00006 | $0.00072 |
Grade A, and why
symphony-pr-feedback scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to symphony-pr-feedback — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR feedback sweep
When to run
- Before transitioning the issue to
In Reviewfor the first time. - After every change prompted by review (push → reviewer reacts → repeat).
- When a
Todoredispatch lands on a PR that already has comments — sweep before doing new work.
Channels
Reviewer feedback arrives across three channels — gather all three:
- Top-level PR comments (issue thread):
pr=$(gh pr view --json number -q .number) repo=$(gh repo view --json nameWithOwner -q .nameWithOwner) gh api --paginate "repos/${repo}/issues/${pr}/comments" - Inline review comments (line-anchored):
gh api --paginate "repos/${repo}/pulls/${pr}/comments" - Review states (approved / changes requested / commented):
gh api --paginate "repos/${repo}/pulls/${pr}/reviews"
--paginate is mandatory: GitHub REST list endpoints page at 30 by default, so a busy PR can silently hide later comments and trick the sweep into declaring "no actionable feedback" when there is.
The Manual QA Plan comment, when present, sharpens UI/runtime coverage — read it before transitioning.
Resolution rules
Treat every actionable comment (human or bot, top-level or inline) as blocking until one of these is true:
- Code/tests/docs updated to address it. Push the fix, then reply where the comment lives (inline reply for inline comments; top-level for top-level) noting the commit SHA.
- Explicit, justified pushback. Reply on the same thread with: acknowledge → rationale → offer alternative or follow-up. Keep it concrete; don't dismiss with "won't do".
Mirror each item and its resolution in the workpad's plan so the trail is auditable.
Replying to inline comments
The endpoint for an inline reply is the pulls endpoint (not issues) and in_reply_to must be the numeric review-comment id, not a GraphQL node id:
gh api -X POST "repos/${repo}/pulls/${pr}/comments" \
-f body='<reply text>' \
-F in_reply_to=<numeric-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.
- 9d ago First seen · 71 lines · 57 tokens per session scan A 00198ff9cc0f
symphony-pr-feedback is a skill published in the GitHub repository anantjain-xyz/symphony-rust (11 stars, last pushed 27d ago), licensed MIT. It adds 57 tokens to every session and 723 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to symphony-pr-feedback, differing in 0 lines, and is treated as a copy.
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…