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 waqas1412/claude-harness --skill workspace-initgit clone --depth 1 https://github.com/waqas1412/claude-harnessWrote 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/waqas1412/claude-harness/workspace-init)<a href="https://agentmods.dev/skills/waqas1412/claude-harness/workspace-init"><img src="https://agentmods.dev/badge/skills/waqas1412/claude-harness/workspace-init/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/waqas1412/claude-harness/workspace-init"><img src="https://agentmods.dev/badge/skills/waqas1412/claude-harness/workspace-init.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 | $0.00000 | $0.02537 |
| Opus 5 | $0.00000 | $0.01269 |
| Sonnet 5 | $0.00000 | $0.00507 |
| Haiku 4.5 | $0.00000 | $0.00254 |
Grade A, and why
workspace-init 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/workspace-init: harness a multi-repo workspace
Bootstrap or refresh navigation for a workspace ROOT whose immediate children are independent git repositories. This skill is a recipe, not an engine: the main loop plans, delegates, and gates. Read-only scan agents fan out concurrently; exactly one sequential executor agent per repo writes files. Do not build a coordinator, daemon, message bus, or worktree fan-out. Invoking this skill by name is the explicit in-the-moment opt-in the global single-main-loop rule requires; it licenses the fan-out described below and nothing else.
This skill produces WORKSPACE-LEVEL artifacts. It complements the single-repo harness-init skill, which produces REPO-LEVEL artifacts inside one repo. Where a child repo already has its own AGENTS.md/CLAUDE.md, treat that as authoritative for the repo and only summarize it here; never overwrite a repo's internal files.
Arguments
- No arg: full workspace scan and generation.
--refresh: regenerate all workspace artifacts from a fresh scan; preserve any hand edits outside generated markers (see Phase 6).- A trailing scope string (e.g. a category name or a space-separated subset of repo slugs): limit deep-index (re)generation to those repos only; the root CLAUDE.md catalog is always regenerated in full so the router stays complete.
Artifacts written
CLAUDE.md(workspace root) from this skill'sassets/workspace-CLAUDE.md.tmpl..claude/repo-index/<repo>.mdper child repo (deep index; read on demand, its targets frontmatter documenting scope) from this skill'sassets/rule.md.tmpl..claude/meta/navigation.mdfrom this skill'sassets/navigation.md.tmpl..claude/harness/seams/clusters.json(cluster + hunter config parameter file for refresh-seams).
Template resolution
This skill ships its own template copies under its assets/ directory (workspace-CLAUDE.md.tmpl, rule.md.tmpl, navigation.md.tmpl) so it is self-contained; resolve each by name relative to this skill's own directory. A workspace-local copy always wins: if .claude/harness/templates/<name>.tmpl already exists in the target workspace, read that instead of the bundled one (same copy-wins convention refresh-seams uses for its own assets).
What ships with it
3 files 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.
- 2d ago Changed 16de92a3a84a
- 10d ago First seen · 94 lines · 0 tokens per session scan A d0b7549f9070
workspace-init is a skill published in the GitHub repository waqas1412/claude-harness (1 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,537 tokens. 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
flame-harness-submit
Phase 10 — upload store text metadata + categories via fastlane, then pause with exact manual steps for the final iOS review submission and Android production promotion.
flame-harness-build
Phase 8 — bootstrap signing credentials, generate fastlane config from templates, and build + upload signed IPA (TestFlight) and AAB (internal track).
fabrik-implement
Use when operating as the Fabrik Implement stage agent. This skill guides the implementation of a planned feature, following the task checklist to produce committed, tested, pushed code on a feature branch.
fabrik-review-comment
Use when operating as the Fabrik Review comment reviewer. This skill guides applying user decisions on review findings — fixing issues, dismissing false positives, or deferring items — then committing and pushing without signaling stage completion.
security-pipeline
Use when security verification is needed - pre-commit security checks, vulnerability scanning, STRIDE threat analysis. Integrates with /handoff-verify --security and /commit-push-pr. CWE Top 25 based.
caveman-commit
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit.…