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 pr-history-hygienegit 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/pr-history-hygiene)<a href="https://agentmods.dev/skills/arch3rpro/dsh-skills/pr-history-hygiene"><img src="https://agentmods.dev/badge/skills/arch3rpro/dsh-skills/pr-history-hygiene/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/pr-history-hygiene"><img src="https://agentmods.dev/badge/skills/arch3rpro/dsh-skills/pr-history-hygiene.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 | $0.00080 | $0.00905 |
| Opus 5 | $0.00040 | $0.00452 |
| Sonnet 5 | $0.00016 | $0.00181 |
| Haiku 4.5 | $0.00008 | $0.00090 |
Grade A, and why
pr-history-hygiene 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 12d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR History Hygiene
Discipline for the lifecycle of a pull request, from preparation through landing. It covers how to split work, how to rewrite history safely, how to label, and how to land a stack of dependent PRs. It applies to any git workflow with pull requests; the platform-specific bits (stacking, labels) generalize to whatever the repo uses.
The defining constraint: history is rewritten only when it is lease-protected — a force-push that aborts if the remote has moved — and never with raw force. Everything else follows from protecting other people's work and the review record.
Choose the history deliberately
- Split independent changes. Each PR is one coherent change; do not bundle unrelated work. When a bug is found in a PR you already published, fix the introducing PR before propagating the fix to dependents.
- Pick the merge strategy per change. After review, an ordinary branch may merge forward or rebase. A history rewrite is allowed after review, but it invalidates every commit-OID assumption — re-audit review threads, approvals, mergeability, and checks afterward.
Rewrite safely — never raw force
Before any history rewrite:
- Fetch the current remote branch and record its exact head.
- Publish with a lease-protected force-push (e.g.
--force-with-lease=<branch>:<observed-head>) so a concurrent update aborts the push instead of being overwritten. - Raw
--forceis never allowed — it silently destroys a concurrent update. - After the push, re-fetch the live heads and re-audit unresolved review threads, approvals, and checks. Commit hashes and inline-comment anchors from before the rewrite are not current evidence.
Label deliberately
Apply one primary label that classifies the change's kind, and every material area label that the change touches. A label is material when the change substantively affects that area; do not over-tag with every area a file happens to live in.
Land a stack through the platform's native stack
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.
- 12d ago First seen · 54 lines · 80 tokens per session scan A 964c262feef9
pr-history-hygiene is a skill published in the GitHub repository arch3rPro/dsh-skills (4 stars, last pushed 25d ago), licensed MIT. It adds 80 tokens to every session and 905 once invoked, about $0.0004 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
pre-publish-review
Nuclear-grade 12-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain agents for deep per-change analysis, invokes /review-work (orchestrator manual QA plus one gate reviewer) for holistic review, and 1 oracle for overall release…
han-release
Cut a Han release: update CHANGELOG.md with the changes since the last release, bump and tag every plugin that changed as {plugin-name}--v{version} so a version-constrained dependency can resolve, and publish a GitHub release crediting every merged pull request and closed issue to the people behind it. Use when…
suede-play-release
Suede Labs Google Play delivery skill: ship an Android release end to end from the agent interface, without opening the Play Console. Set up credentials, upload an AAB, promote between tracks, stage or complete a rollout, push per-locale release notes, and prove against the Play Developer API what is actually live.…
suede-launch-packaging
Suede-owned launch packaging and install verification. Use when finished software work needs a clean public package — README, docs page, install command, release note, GitHub Pages update, skill-pack release, MCP server, or launch/social copy — or when a release needs handoff notes, an install fails, a public user…
log-changes
Use when asked to update the changelog, document version changes, prepare a release, or add entries for recent work, and when reviewing a diff or pull request that touches CHANGELOG.md. Produces concise user-facing CHANGELOG.md entries, follows Keep a Changelog and Semantic Versioning, and verifies that new bullets…
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…