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 arch3rPro/dsh-skills --skill responding-to-review-on-a-stackgit clone --depth 1 https://github.com/arch3rPro/dsh-skillsWrote 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/arch3rpro/dsh-skills/responding-to-review-on-a-stack)<a href="https://agentmods.dev/skills/arch3rpro/dsh-skills/responding-to-review-on-a-stack"><img src="https://agentmods.dev/badge/skills/arch3rpro/dsh-skills/responding-to-review-on-a-stack/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/arch3rpro/dsh-skills/responding-to-review-on-a-stack"><img src="https://agentmods.dev/badge/skills/arch3rpro/dsh-skills/responding-to-review-on-a-stack.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 | $0.00071 | $0.00863 |
| Opus 5.5 | $0.00028 | $0.00345 |
| Sonnet 5.5 | $0.00014 | $0.00173 |
| Haiku 4.5 | $0.00007 | $0.00086 |
Grade A, and why
responding-to-review-on-a-stack 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 1mo 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Responding to Review on a Stack
A discipline for acting on review comments that span several PRs in a dependent stack (A ← B ← C …). It owns review-fix placement and propagation; pr-history-hygiene owns linkage checks and landing, and code-review owns finding the issues.
The defining constraint: a fix lands on the PR that introduced the issue, then flows up-stack — never downstream, where the introducing PR ships the unfixed code and the fix is hidden from its reviewer.
Ground rules
- One worktree per PR branch. Each PR's fixes happen in that PR's own worktree; parallel fixes never share a checkout.
- The stack object is authoritative. Base branches establish the expected dependency order; the platform's stack metadata proves it is recognized. Do not treat a matching branch chain as an official stack without checking that metadata.
- A fix lands on the introducing PR, then flows up-stack. When a comment on PR
Bpoints at codeBintroduced, fix it onBand propagate intoC— even ifCalso carries the file. - Each review fix remains a distinct commit. A later rebase may change its OID, but do not amend a reviewed fix out of the branch history. Amend only your own not-yet-pushed, not-yet-reviewed work.
- Choose merge-forward or rebase deliberately. Both are allowed after review. A rewritten push must be lease-protected and must abort rather than overwrite a concurrently advanced remote head; raw force is forbidden.
Resolve comments through the stack
- Triage every comment on the merits before acting: verify the claim against the code — a reviewer flagging the right symptom can still misdiagnose the cause.
- Map each accepted finding to its originating PR and fix it there.
- Propagate the fixed layer through every affected child in order — merge-forward (merge the fixed parent into the child, validate, continue upward) or a native cascading rebase (validate the rewritten layers, then publish).
- Trust but verify delegated fixes — a sub-agent's report describes intent, not necessarily what landed. Re-run the gates on the actual tree; prove a regression guard fails on the unfixed code.
- Reply in the review thread, not as a top-level comment, stating the fix and the current commit or head that carries it.
- After any rewritten push, re-read unresolved threads, approvals, mergeability, and checks. A force-pushed OID or outdated inline anchor is not current evidence that the finding remains resolved.
What ships with it
1 file 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.
- 1mo ago First seen · 45 lines · 71 tokens per session scan A d29da1c2ce66
responding-to-review-on-a-stack is a skill published in the GitHub repository arch3rPro/dsh-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 71 tokens to every session and 863 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 2026-08-31.
Other skills, from other repositories
suede-code
Use when explicitly asked "review this PR" or to grade a diff, branch, or commit range. Suede AI returns evidence-backed P0-P3 findings, fix paths and an A-F ship grade; supports findings-only, grade-only and fix modes, seven review lanes, security checks, deploy safety and commit dirt. NOT FOR: automatic CI…
review-arch
Conduct a principal-level architecture review of a system, specification, diagram, or set of design decisions. Use when asked to review an architecture, evaluate a design, assess coupling/cohesion, check for anti-patterns, audit system boundaries, or produce an Architecture Review Board (ARB) style verdict. Also use…
review-impl
Review implementation changes for a given task against architectural standards. Use when reviewing a PR, evaluating recently committed code, assessing whether implementation changes are correct and architecturally sound, or when asked to 'review my changes', 'check this implementation', 'review what I built', 'is this…
python-anti-patterns
Common Python anti-patterns and a pre-merge review checklist.
address-review
Work through review findings on a PR one at a time.
babysit-pr
Resolve reviewer comments on a pull request or pasted feedback using a six-step evidence-grounded protocol. Use when asked to resolve review feedback, address reviewer comments, process PR comments, triage review feedback, apply review suggestions, handle code review feedback, decide which review comments to accept or…