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 conorbronsdon/agent-workspace --skill recovergit clone --depth 1 https://github.com/conorbronsdon/agent-workspaceWrote 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/conorbronsdon/agent-workspace/recover)<a href="https://agentmods.dev/skills/conorbronsdon/agent-workspace/recover"><img src="https://agentmods.dev/badge/skills/conorbronsdon/agent-workspace/recover/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/conorbronsdon/agent-workspace/recover"><img src="https://agentmods.dev/badge/skills/conorbronsdon/agent-workspace/recover.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 | $0.00030 | $0.01148 |
| Opus 5.5 | $0.00012 | $0.00459 |
| Sonnet 5.5 | $0.00006 | $0.00230 |
| Haiku 4.5 | $0.00003 | $0.00115 |
Grade A, and why
recover 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.
This is a copy
89% identical to recover — 52 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/recover — Worktree & Branch Cleanup
Scan for orphaned worktrees, stale branches, and partial work left behind by crashed or abandoned agent sessions. Read-only by default — reports findings and waits for approval before any cleanup.
Invocation: deliberately model-invocable — scanning is read-only. Every cleanup action is gated on explicit user approval.
Configuration
This skill operates on git worktrees and branches only; it reads no state files, so
workspace.yaml's state paths do not apply. The one setting it depends on is the default
branch, which it detects (step 0) rather than hardcoding. Full reference:
docs/state-model.md.
When to Use
- After a system crash or forced session termination
- When parallel-session hooks warn about stale processes
- When you find commits on unknown branches
- Periodic hygiene (monthly, or after heavy parallel work)
Instructions
0. Detect the default branch
Don't assume main. Resolve it once and use it everywhere below:
git rev-parse --git-dir >/dev/null 2>&1 || { echo "not a git repository — nothing to recover"; exit 0; }
DEFAULT=$(git symbolic-ref --short refs/remotes/origin/HEAD 2>/dev/null | sed 's|^origin/||')
DEFAULT=${DEFAULT:-$(git remote show origin 2>/dev/null | sed -n 's/.*HEAD branch: //p')}
DEFAULT=${DEFAULT:-main} # no remote at all — fall back and note it in the report
1. List all worktrees
git worktree list --porcelain
Identify:
- Recently touched worktrees: files or
.gitmetadata modified in the last hours — treat as possibly live.git worktree listcannot tell whether a session is actually running; without a lock/heartbeat file or process evidence, classify as unknown activity and never as orphaned. - Candidate-orphaned worktrees: no recent modification and no activity signal — proceed to inspection, still gated on user approval before any cleanup.
- Stale entries: git tracks a worktree but the directory is gone.
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 · 134 lines · 30 tokens per session scan A f1d91b9d7d25
recover is a skill published in the GitHub repository conorbronsdon/agent-workspace (2 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 1,148 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 89% identical to recover, differing in 52 lines, and is treated as a copy.
Other skills, from other repositories
self-extension-workflow
Apply when executing the self-extension workflow. Six steps from a mistake to a merged rule, with CI gates and CODEOWNERS approval.
branch-finishing
Apply when closing out a feature branch — pre-merge checklist, rebase, CI verification, cleanup, and post-merge steps.
github-cli
Apply when using the gh CLI to manage pull requests, issues, releases, or CI workflows on GitHub.
git-conventions
Apply when committing, branching, or opening a pull request. Conventional commit format, branch naming, PR scope.
github
GitHub and Git workflow helpers, Issues and Projects v2 management via gh CLI; triggers on 'github', 'create issue', 'list issues', 'github project', 'project board', 'sync tasks', 'create pr', 'pr checks', 'retrigger tests', 'bump version', 'push'.
datalad
Retrieves, versions, and publishes scientific datasets with DataLad and git-annex, and captures computational provenance with datalad run, rerun, and containers-run. Use when cloning or fetching data from OpenNeuro, DANDI, datasets.datalad.org, or any DataLad dataset; when a file in a dataset reads as a broken symlink…