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 ychampion/cskill-agents --skill reachable-wip-via-temporary-refsgit clone --depth 1 https://github.com/ychampion/cskill-agentsWrote 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/ychampion/cskill-agents/reachable-wip-via-temporary-refs)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/reachable-wip-via-temporary-refs"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/reachable-wip-via-temporary-refs/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/ychampion/cskill-agents/reachable-wip-via-temporary-refs"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/reachable-wip-via-temporary-refs.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 | $0.00038 | $0.00555 |
| Opus 5 | $0.00019 | $0.00278 |
| Sonnet 5 | $0.00008 | $0.00111 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
reachable-wip-via-temporary-refs 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 8d 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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Reachable WIP Via Temporary Refs
Domain: safety-worktrees
Trigger: Apply when bundling or seeding a repository and you want to include uncommitted work without disturbing the working tree or leaving dangling refs.
Source Pattern: Distilled from reviewed repo-safety, packaging, and worktree-management patterns.
Core Method
Call git stash create to materialize the working tree and index into a temporary commit while leaving the workspace untouched. If the command returns a SHA then advertise it via a short-lived ref such as refs/seed/stash so downstream tooling (bundle list-heads, receivers) can reach those objects; treat an empty response as “no WIP,” log both success and error cases, and clean up the temporary ref after the upload completes or earlier runs leave stale pointers.
Key Rules
- Always run the ref cleanup loop (
refs/seed/stash,refs/seed/root) before bundling so previous runs do not influence new bundles or leak stale WIP markers. - Accept that
git stash createcan fail non-fatally; log the stderr, skip ref creation, but continue bundling the committed tree. - Only call
git update-ref refs/seed/stash <sha>when the stash SHA is non-empty; otherwise the ref would dereference to nothing. - Record a boolean flag (
hasWip) when the temporary stash exists so telemetry and later steps can know whether to expect extra objects. - After the bundle (and after the
finallyblock), delete the temporary refs even if the upstream run failed to keep the user repo clean.
Example Application
When writing an upload helper for a CLI that seeds a remote CCR process, use this skill to wrap the git stash create/git update-ref pair, expose hasWip, and ensure the finally block always runs git update-ref -d refs/seed/stash before returning.
Anti-Patterns (What NOT to do)
- Do not rely on the regular stash stack (refs/stash) because
git bundleshould not touch the user-visible stack;git stash createavoids a working-tree mutation. - Do not advertise an empty SHA: bundlers that list heads will fail to find objects.
- Do not skip cleanup: leaving
refs/seed/stashbehind pollutes the repo and may cause future bundling runs to include WIP twice.
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.
- 8d ago First seen · 30 lines · 38 tokens per session scan A 45c2a9a3aa95
reachable-wip-via-temporary-refs is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 38 tokens to every session and 555 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 2026-09-03.
Other skills, from other repositories
repo-hygiene
Use when auditing repo hygiene in any codebase — file layout, git history, config sprawl, ignore contracts, open-source readiness. Assess by default, fix on request; treats the repository as a product whose users are contributors.
agentplane-release-and-packaging-operator
Use when preparing, validating, publishing, auditing, or recovering an Agentplane release, especially package build ordering, version parity, npm/GitHub/GHCR/external distribution publication, public install smoke tests, hosted publish evidence, or release CI failures.
agentplane-task-closure-recovery
Use when Agentplane task completion, direct finish, branchpr integration, hosted-close, close-tail PRs, PR metadata, dirty task artifacts, or remote branch divergence need diagnosis or recovery.
agentplane
Use when a repository uses AgentPlane or the user wants a governed git-native workflow for planning, task execution, verification, and closure.
genie-orca-work
Coordinator loop for an approved wish on Orca — one Run per wish, one Task per group, supervised workers in child worktrees, review→fix loops, Linear written only at gate transitions. genie v6 'corpo leve': genie owns the documents and this protocol; Orca owns dispatch state; Linear owns status; brain owns preferences.
grape
Use Grape MCP for Codex context continuity in coding repositories. Use when a task needs repeated-turn context, omitted context restore, stale-context checks, invalidation checks, or safe continuity across branch and dirty-worktree changes.