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 ZaxbyHub/opencode-swarm --skill parallel-work-checkgit clone --depth 1 https://github.com/ZaxbyHub/opencode-swarmWrote 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/zaxbyhub/opencode-swarm/parallel-work-check)<a href="https://agentmods.dev/skills/zaxbyhub/opencode-swarm/parallel-work-check"><img src="https://agentmods.dev/badge/skills/zaxbyhub/opencode-swarm/parallel-work-check.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 92 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Agent Snooping · line 124 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 126 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00041 | $0.01293 |
| Opus 5 | $0.00020 | $0.00647 |
| Sonnet 5 | $0.00008 | $0.00259 |
| Haiku 4.5 | $0.00004 | $0.00129 |
Grade A, and why
parallel-work-check 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 5d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel Work Check Protocol
Run this check before starting ANY work on an existing branch (not a fresh branch you just created). This applies to PR branches, feature branches, and any branch that may have concurrent contributors.
Step 1 — Check current branch state
- Determine the current branch name.
- Determine the remote tracking branch (usually
origin/<branch-name>).
Step 2 — Fetch remote state
Fetch the latest state from the remote for the current branch. Do NOT skip this step because "the branch looks recent" or "I just checked."
Step 3 — Compare local vs remote
Compare the local HEAD commit hash with the remote HEAD commit hash:
- Identical: Remote has not diverged. Proceed with your work.
- Remote ahead: The remote branch has commits you don't have locally.
- Read the new commit messages with
git log local..remote. - Check if any of those commits touch files you plan to modify.
- If yes: evaluate whether the parallel work supersedes your planned changes.
- If the parallel work is superior: reset your local branch to match remote and abandon your planned approach. Document the decision.
- If the parallel work is complementary: integrate it first, then proceed.
- Read the new commit messages with
- Local ahead: You have local commits not on remote. This is normal if you already started work. Proceed, but be aware that pushing may conflict with subsequent remote changes.
- Diverged: Both local and remote have unique commits. This requires integration. Merge or rebase as appropriate for the team's workflow.
Step 4 — Check for parallel swarm/agent work
If the remote has new commits:
- Check the commit authors. If commits are from a different swarm/agent (different author name/email pattern), treat this as parallel swarm work.
- Parallel swarm work is often superior because:
- It may have access to different context or tools
- It may have started earlier or had more iterations
- It may have taken a fundamentally better approach
- Default stance: prefer the parallel swarm's work unless you can clearly articulate why your approach is better.
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.
- 5d ago First seen · 134 lines · 41 tokens per session scan A 30a92c03a717
parallel-work-check is a skill published in the GitHub repository ZaxbyHub/opencode-swarm (466 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 1,293 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
create-issue
Draft and submit a GitHub issue from a user idea or bug description, with bilingual body and correct labels.
armada-gate
Run an evidence-gate checklist for each success criterion in the current phase. Use when checking if a phase is complete before marking it passed.
armada-voyage-finish
Voyage-finalization ritual. Load at voyage end, dispatch a galleon subagent to rebase, fix TODO PR refs, regen scaffold, push, open/update PR. Triggers on: finish voyage, finalize, rebase, PR.
armada-pr
PR-first finish for a feature lane. Use before reporting a feature done. Triggers on: PR, finish feature, gh pr create, merge, lane complete.
factory-handoff
Hand one exact agent-ready ticket to the central Factory runtime over the configured SSH forced-command boundary. Use when an operator asks to hand off an existing ticket or a prose request instead of implementing it in the current session.
creating-issues-and-pull-requests
Use when creating GitHub pull requests or issues with template compliance. Triggers: 'create a PR', 'open a pull request', 'file an issue', 'create issue'. Also invoked by finishing-a-development-branch. NOT for: deciding whether to merge or PR (use finishing-a-development-branch).