Borrowing it
Nothing to install: this file belongs to vscarpenter/gsd-task-manager. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vscarpenter/gsd-task-manager/main/.agents/skills/reviewable-pr-slicing/SKILL.mdgit clone --depth 1 https://github.com/vscarpenter/gsd-task-managerWrote 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/vscarpenter/gsd-task-manager/reviewable-pr-slicing)<a href="https://agentmods.dev/skills/vscarpenter/gsd-task-manager/reviewable-pr-slicing"><img src="https://agentmods.dev/badge/skills/vscarpenter/gsd-task-manager/reviewable-pr-slicing/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/vscarpenter/gsd-task-manager/reviewable-pr-slicing"><img src="https://agentmods.dev/badge/skills/vscarpenter/gsd-task-manager/reviewable-pr-slicing.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 | $0.00068 | $0.00905 |
| Opus 5 | $0.00034 | $0.00452 |
| Sonnet 5 | $0.00014 | $0.00181 |
| Haiku 4.5 | $0.00007 | $0.00090 |
Grade A, and why
reviewable-pr-slicing 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
reviewable-pr-slicing
Use this skill when a plan is ready to implement, but the work should be split into small PRs instead of one broad change.
This skill only changes repository artifacts. It may document manual prerequisites, but it must not perform external account setup, store secrets, or change settings outside the repo.
Good fits
- A plan that already has goals, non-goals, and a target state.
- Work that affects multiple layers, such as scripts, workflows, docs, tests, and runtime code.
- Security findings that should land as narrow remediation tranches.
- Refactors that need behavior-preserving setup before behavior-changing work.
- Documentation plus implementation rollouts where reviewers need a clean breadcrumb trail.
Do not use this for tiny fixes, speculative ideas, or work without a clear stopping condition.
Required inputs
Before editing code, collect:
- Approved plan or issue path.
- Current behavior and affected surfaces.
- Goals and non-goals.
- Locked decisions and open decisions.
- Manual prerequisites the human must complete outside the repo.
- Validation commands.
- Manual acceptance tests.
- Rollback or fallback posture.
If these are missing, add them to the plan first and stop before implementation.
Phase design rules
- Keep each PR independently understandable.
- Prefer one concern per PR.
- Put plan-only documentation before implementation.
- Put shared foundations before files that consume them.
- Put read-only validation before write-path changes.
- Put lower-risk environments or paths before higher-risk ones.
- Keep manual prerequisites explicit and separate from code behavior.
- Stop after the current phase. Do not sneak in the next phase.
Default phase pattern
Adapt the names to the work, but start here:
- Plan PR — canonical plan, options, decisions, phase list. No behavior change.
- Foundation PR — shared helpers, scripts, types, or docs scaffolding. Preserve behavior.
- Validation PR — checks, tests, assertions, or reports that make later change safer.
- First behavior PR — narrow live behavior change with the smallest blast radius.
- Second behavior PR — next scoped behavior change after the first proves clean.
- Cleanup PR — remove old paths only after the replacement has been validated.
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 · 115 lines · 68 tokens per session scan A c20570f40a04
reviewable-pr-slicing is a skill published in the GitHub repository vscarpenter/gsd-task-manager (25 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 905 once invoked, about $0.0003 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
polish-docs-meta
Finalize documentation and project metadata for a ship-ready release. Use after implementation is complete, tests pass, and devcheck is clean. Safe to run at any stage — each step checks current state and only acts on what still needs work.
release-and-publish
Ship a release end-to-end across every registry this project targets (npm, MCP Registry). Runs the final verification gate, pushes commits and tags, then publishes to each applicable destination. Assumes git wrapup (version bumps, changelog, commit, annotated tag) is already complete — this skill is the post-wrapup…
memory-commit
Use when the user explicitly says "remember this", "save this", "ghi nho", "luu lai", "save for next time", or otherwise asks to persist the immediately preceding context. Captures with the appropriate contexttype (decision, preference, fact, skill, task, conversation) so future sessions can retrieve it accurately.
feedback-nudge
Use when the user wants to report a bug, request a feature, or send feedback to the Zooza engineering team. Also offer proactively after a successful commit operation (max once per week).
publish-release
Releases a new McpOrchestrator version end to end — version bump PR, tag, and the automated deploy to GitHub Releases, NuGet, and the MCP Registry. Use when asked to release, publish, deploy, ship, or bump the version of McpOrchestrator.
release-notes
Writes user-facing release notes from a git commit range. Use when asked to draft release notes, a changelog entry, or "what's new" text for a release.