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 randommonicle/claude-skills --skill parallel-work-recongit clone --depth 1 https://github.com/randommonicle/claude-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/randommonicle/claude-skills/parallel-work-recon)<a href="https://agentmods.dev/skills/randommonicle/claude-skills/parallel-work-recon"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/parallel-work-recon/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/randommonicle/claude-skills/parallel-work-recon"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/parallel-work-recon.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 | $0.00192 | $0.01070 |
| Opus 5 | $0.00096 | $0.00535 |
| Sonnet 5 | $0.00038 | $0.00214 |
| Haiku 4.5 | $0.00019 | $0.00107 |
Grade A, and why
parallel-work-recon 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel-work recon
Eight incidents of duplicated work, colliding identifiers, and edits landing in trees that no longer existed — plus five more where a session or subagent silently edited the wrong checkout. All from one cause: treating a snapshot of repo state as a lease on it. Layer: session-boundary hub; the session-start half is mechanised by the SessionStart hook (hooks/session-recon.mjs), which injects live state at session open.
The recon
At session start AND again immediately before any commit, merge, or identifier claim:
git fetch --quiet
git log --oneline --decorate --all -8
gh pr list --state open
The pre-commit re-run is the sharp edge. The session-start check (even the hook's) is a
snapshot, not a lease — another machine or session may have pushed while you worked. A
session once nearly rebuilt a fully-shipped PR because it trusted a stale handover; another
inferred a migration was "phantom" when it was simply unpushed (git ls-remote before
inferring absence).
Sequential identifiers
Migration numbers, version strings, and anything else claimed by "next in sequence" collide
silently under parallel work — git flags nothing when two branches ship the same numbers.
Claim by scanning ALL refs including remote, at merge time, not just when the file is
created. A 009*-style glob can misread the ceiling; list and sort, don't pattern-guess.
Worktrees and checkouts
- One session per working copy. Two sessions on one clone halves the snapshot's half-life.
- Use
git -C <path>exclusively for worktree git operations — acdbetween tool calls silently lands elsewhere. - Any prompt handed to a subagent that must work in a worktree states the absolute path and a branch-check first step; audit the paths in its report to confirm which checkout it actually edited (a subagent once edited seven files on main).
- A stale dev server serves the old tree; restart it after switching checkouts.
- Staging is per absolute path:
git add app/srcin the wrong checkout stages nothing you meant.
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 · 77 lines · 0 tokens per session scan A 6b15a9ce1e1a
parallel-work-recon is a skill published in the GitHub repository randommonicle/claude-skills (23 stars, last pushed 4d ago), licensed Apache-2.0. It adds 192 tokens to every session and 1,070 once invoked, about $0.0010 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
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
nvca-chart-release
Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.