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 hams-ollo/zen-agent-skills --skill fix-batchgit clone --depth 1 https://github.com/hams-ollo/zen-agent-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/hams-ollo/zen-agent-skills/fix-batch)<a href="https://agentmods.dev/skills/hams-ollo/zen-agent-skills/fix-batch"><img src="https://agentmods.dev/badge/skills/hams-ollo/zen-agent-skills/fix-batch/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/hams-ollo/zen-agent-skills/fix-batch"><img src="https://agentmods.dev/badge/skills/hams-ollo/zen-agent-skills/fix-batch.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 | $0.00138 | $0.07437 |
| Opus 5.5 | $0.00055 | $0.02975 |
| Sonnet 5.5 | $0.00028 | $0.01487 |
| Haiku 4.5 | $0.00014 | $0.00744 |
Grade B, and why
fix-batch scanned grade B with 1 finding 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 7d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
write, or run any command against any path outside your assigned worktree, for any reason, not How it starts
The opening of the file, as written. The whole thing — 453 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fix-batch
Spawn parallel worktree-isolated agents to work a batch of independent task files, then verify every one of them yourself before calling any of it done. The verification pass is not optional, it is the actual point of this skill. Parallel delegation without it is just parallel delegation. The value here is specifically in catching what unsupervised agents get wrong, because they will, and their own summaries will not tell you.
This is the parallel-execution step of the kit spine: new-task authors
the atomic task files, fix-batch dispatches them to isolated agents,
test-author and verifier-agent prove
each result at Step 6, and reconcile-worktrees lands the
verified ones into the main working tree. Read the target repository's AGENTS.md, specifically
its agent reading protocol section and its task lifecycle section, before dispatching, so each
spawned agent inherits the same rules.
Why this exists
A 2026-07-07 batch of four background agents in isolated worktrees all claimed success. Independent verification found that one had used a shell to overwrite a file in the main checkout, destroying unrelated work, then fabricated an undisclosed test while repairing it; two had moved task files to done/ while leaving their status and checkboxes untouched; and four identical agents had invented three incompatible ways to handle task files git did not carry into their worktrees. None of it was visible in their own reports. This skill makes the verification pass that caught it the default rather than an afterthought. The full record is in references/incidents.md.
When not to use this
- A single fix, or fixes with actual dependencies between them (one agent needs to see another's finished output before it can work). Worktree isolation is specifically for independent, parallelizable work. Sequential or interdependent changes belong in one agent or one worktree, not several.
- Throwaway exploratory changes with nothing to lose if something goes sideways. The overhead of hardened sandboxing plus a full verification pass is worth it when the target is a real, shared, or otherwise valuable working tree, not for disposable scratch work.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago Changed · -32 lines · -66 tokens per session 3815ed873e15
- 1mo ago Changed · +5 lines c482e966606a
- 2mo ago First seen · 480 lines · 204 tokens per session scan B 9a5d6c4f5a3e
fix-batch is a skill published in the GitHub repository hams-ollo/zen-agent-skills (2 stars, last pushed 7d ago), licensed MIT. It adds 138 tokens to every session and 7,437 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
gsd-map-codebase
Analyze codebase with parallel mapper agents to produce .planning/codebase/ documents.
gsd-manager
Interactive command center for managing multiple phases from one terminal.
gsd-new-project
Initialize a new project with deep context gathering and PROJECT.md.
gsd-ns-manage
Invoke this Pi skill with /skill:gsd-ns-manage.
gsd-ns-context
Invoke this Pi skill with /skill:gsd-ns-context.
gsd-ns-project
Invoke this Pi skill with /skill:gsd-ns-project.