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 agentmods add skills/christopherlouet/claude-base/work-batchnpx skills add christopherlouet/claude-base --skill work-batchgit clone --depth 1 https://github.com/christopherlouet/claude-baseWrote 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/christopherlouet/claude-base/work-batch)<a href="https://agentmods.dev/skills/christopherlouet/claude-base/work-batch"><img src="https://agentmods.dev/badge/skills/christopherlouet/claude-base/work-batch.svg" alt="Measured on agentmods" 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 | $0.00047 | $0.00717 |
| Opus 5 | $0.00023 | $0.00358 |
| Sonnet 5 | $0.00009 | $0.00143 |
| Haiku 4.5 | $0.00005 | $0.00072 |
Grade A, and why
work-batch 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 2d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Batch Execution Mode
Autonomous and sequential execution of user stories from a PRD file.
PRD file format
JSON (prd.json)
{
"project": "project-name",
"stories": [
{
"id": "US-001",
"title": "Story title",
"description": "Detailed description",
"priority": "P1",
"acceptance_criteria": [
"Given X, When Y, Then Z"
],
"files": ["src/module.ts", "src/module.test.ts"]
}
]
}
Markdown (prd.md)
## US-001: Story title
**Priority**: P1
**Description**: Detailed description
**Acceptance criteria**:
- Given X, When Y, Then Z
**Files**: src/module.ts, src/module.test.ts
Workflow per story
For each story in priority order (P1 → P2 → P3):
1. LOAD - Load the story
- Read the story from the PRD file
- Display the title and description
- Check prerequisites (files, dependencies)
2. IMPLEMENT - TDD cycle
- Write the tests first (RED)
- Implement the minimal code (GREEN)
- Refactor if necessary (REFACTOR)
- Verify the acceptance criteria
3. COMMIT - Save
- Run the tests:
npm test/pytest/go test - If tests OK: commit with
feat(scope): US-XXX description - If tests KO: STOP and report the blocker
4. REPORT - Update the state
- Mark the story as done in
.claude/output/batch/progress.json - Log the time and modified files
- Move on to the next story
Progress file
Automatic save in .claude/output/batch/progress.json:
{
"started_at": "2026-03-23T10:00:00Z",
"stories": {
"US-001": { "status": "done", "commit": "abc1234", "files": ["..."] },
"US-002": { "status": "in_progress" },
"US-003": { "status": "pending" }
}
}
Resume after interruption
If progress.json exists, resume at the last in_progress or pending story.
Guardrails
- Maximum 10 stories per batch (beyond that, split)
- STOP if 2 consecutive stories fail
- Each story must pass the tests before continuing
- Commit after each story (no giant commits)
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.
- 2d ago First seen · 116 lines · 47 tokens per session scan A 8716d88fe73b
work-batch is a skill published in the GitHub repository christopherlouet/claude-base (5 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 717 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
moai-ref-git-workflow
Git workflow patterns, branch strategies, conventional commits, and PR templates reference for git operations. Agent-extending skill that amplifies manager-git expertise with production-grade git workflow patterns. NOT for: code implementation, testing, architecture design, documentation content.
core-workflow
Detailed development workflow patterns, checklists, and standards. Auto-loads for complex tasks, planning, debugging, testing, or when explicit patterns are needed. Contains session protocols, git conventions, security checklists, testing strategy, and communication standards.
git-workflow
Use when naming or scoping a branch, writing or fixing a commit message, picking the gitmoji for a commit, untangling history (rebase versus merge versus squash), or cutting a versioned release — the portable git-convention layer for any repo. Covers gitmoji + Conventional Commits, SemVer tags, branch hygiene…
session-start
Use this skill when initializing a session for any project repo. Autonomously analyzes git state, VCS issues, SSOT files, branches, environment, and cross-repo status. Then presents structured findings with recommendations for user alignment before creating a wave plan. Triggered by /session…
spinout
Use when extracting a project into its own repo — a venture spinout (e.g. a product leaving its incubator repo) or a sanitized content-snapshot fork. Guided 5-step runbook: target sphere + path, confidentiality/sanitize check, copy + fresh git init, SNAPSHOT-FREEZE marker in the source repo, remotes + registration.…
session-end
Use this skill when performing a full session close-out: verifies all planned work against the agreed plan, creates issues for gaps, runs quality gates, commits cleanly, mirrors to GitHub, and produces a session summary. Triggered by /close command.