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/scolladon/craft/workspacenpx skills add scolladon/craft --skill workspacegit clone --depth 1 https://github.com/scolladon/craftWrote 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/scolladon/craft/workspace)<a href="https://agentmods.dev/skills/scolladon/craft/workspace"><img src="https://agentmods.dev/badge/skills/scolladon/craft/workspace.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 | $0.00027 | $0.00547 |
| Opus 5 | $0.00014 | $0.00273 |
| Sonnet 5 | $0.00005 | $0.00109 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
workspace scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
craft:workspace
Preamble (always runs — non-overridable)
"${CRAFT_ROOT:-${CLAUDE_PLUGIN_ROOT}}/scripts/manifest-lint.sh"must pass; read the manifest.- Probe: git repo present (else STOP — craft needs one); default branch
(
origin/HEAD→main→master→ ask once). - Memory read/write surface (advisory).
READS: last
toolchainentry for this repo (ecosystem + lockfile fingerprint). If the fingerprint matches the current lockfile, skip re-detection for the already-known ecosystem — still re-detect on a miss or a changed fingerprint. WRITES (buffered to run record, flushed at run end): the detected ecosystem + lockfile fingerprint produced byscripts/worktree-setup.shlockfile detection. The hint never gates — a miss falls through to full detection as today.
Procedure (default body — a manifest override: replaces everything below)
- Infer the branch type from the brief (
feat/fix/chore, defaultfeat). - Consult
isolateaction (defaultalways, ADR-127 — proceeds silently unless policy forbids it; seedocs/contributing/specs/policy.mdfor surface semantics). Then, strategyworktree(default):
Strategygit worktree add ../<repo>-<slug> -b <type>/<slug> "${CRAFT_ROOT:-${CLAUDE_PLUGIN_ROOT}}/scripts/worktree-setup.sh" <abs-worktree-path> [manifest scripts.post-setup]in-place(manifestworkspace: { strategy: in-place }): create the branch in the current checkout (git switch -c <type>/<slug>); deps assumed present or installed in place; later phases use the checkout root wherever they'd use the worktree (run-lock location included). - Branch or worktree path collision → STOP and ask; never reuse silently.
- Apply the manifest's global/workspace
context:file now: perform any tooling activation it declares (the session does this — agents will receive the same file and must find the tooling already active). Its teardown counterpart runs at integrate. - All subsequent work happens ONLY in this worktree/branch.
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.
- 4d ago First seen · 40 lines · 27 tokens per session scan A 8c28ebc54461
workspace is a skill published in the GitHub repository scolladon/craft (2 stars, last pushed 16d ago), licensed MIT. It adds 27 tokens to every session and 547 once invoked, about $0.0001 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
great_cto
Use when the CTO describes a feature, task, or project goal. Orchestrates the full SDLC pipeline automatically based on project type.
vertical-real-estate
Residential-proptech domain knowledge so architect / pm aren't naive when speccing real-estate products (listings, lead-crm, transaction-coordination, property-mgmt). Codifies MLS/IDX reality, listing status lifecycle + syndication canonical-source, long-cycle lead nurture, transaction-coordination as the high-pain…
skeptical-triage
Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of 4 extra LLM turns.
anti-patterns
Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).
cost-model
Standardized cost-estimation framework for greatcto plans. Forces explicit LLM cost, infra cost, human-supervision time, and the (defensible) human-equivalent comparison. Output format is parsable by the board's /api/cost path — must follow exactly.
pm-planning
Decomposition methodology for pm agent — turns an approved ARCH document into a Beads task list with explicit dependencies, time-boxes, and acceptance criteria. The pipeline can only orchestrate work it can see; this skill defines what "seeable work" looks like.