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/slowdoctor-dev/workspace-md/initnpx skills add slowdoctor-dev/workspace-md --skill initgit clone --depth 1 https://github.com/slowdoctor-dev/workspace-mdWhat 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 | $0.00065 | $0.01517 |
| Opus 5 | $0.00032 | $0.00758 |
| Sonnet 5 | $0.00013 | $0.00303 |
| Haiku 4.5 | $0.00006 | $0.00152 |
Grade A, and why
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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
init
When to use
Once after cloning a workspace.md-compliant workspace, or after major
filesystem reorganization, or after switching the primary runtime
(e.g., moving from local-only Ollama to a hosted CLI). Not for
routine sessions (use session-start).
Requires
Requires AGENTS.md and WORKSPACE.md at the repo root. During
bootstrap, verify 3-control/foundation/SOUL.md,
3-control/foundation/PRINCIPLE.md, and 2-mind/garden/essential/.
If any of those are missing, stay in init and restore from git or a
fresh clone before invoking lifecycle skills.
Quick reference
| Step | Reads | Writes |
|---|---|---|
| 1. Verify structure | WORKSPACE.md, repo file tree |
— |
2. Invoke detect-runtime (bootstrap mode) |
runtime self-introspection + env/config/endpoint signals | — (skill returns proposed profile) |
| 3. Ratify profile.md | detect-runtime result + 3-control/runtime/profile.example.md |
3-control/runtime/profile.md (T2 active state) |
| 4. (Optional) expose Antigravity aliases | ratified harness=antigravity, MCP registry |
.agents/ aliases/rendered config (Owner-owned setup) |
| 5. Brief read order | 3-control/foundation/use-driven-memory.md §Read order |
— |
| 6. (Optional) modify seeds | template files in garden/essential/ |
minor edits only |
Procedure
1. Verify mandated structure
Confirm presence:
- 4 top folders:
0-storage/ 1-active/ 2-mind/ 3-control/ 2-mind/garden/(mandated — declarative memory)2-mind/forge/(mandated — procedural memory)3-control/foundation/SOUL.md(canonical identity)3-control/foundation/PRINCIPLE.md(operating principles)
If anything missing: restore from git or re-clone. Do NOT create missing files — they should be in the spec repo.
2. Invoke detect-runtime (bootstrap mode)
Run the detect-runtime skill
(2-mind/forge/act/skill/detect-runtime/SKILL.md) in bootstrap
mode. It produces a proposed profile with 6 fields populated:
harness, backend_provider, backend_endpoint, backend_model,
effective_context, recommended_tier (derived per
runtime-flexibility.md's canonical rule — becomes active_tier
in active profile.md on Owner ratify), plus any signal_disagreements
flagged.
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 · 139 lines · 65 tokens per session scan A ecee4265d1ce
init is a skill published in the GitHub repository slowdoctor-dev/workspace-md (1 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 65 tokens to every session and 1,517 once invoked, about $0.0003 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
company-brain
How an agent should operate as one mind inside a shared Company Brain built on Caura — recall before acting, obey fleet keystones, reuse and publish skills, and report outcomes so every task compounds across the whole organization. Use this whenever you work as part of a Caura-connected team or fleet and your work…
plan
Plan mode: write markdown plan, no execution.
requesting-code-review
Pre-commit review: security scan, quality gates, auto-fix.
consulting-analysis
Consulting-grade research reports: framework + final report.
research-paper-writing
ML paper pipeline: experiment design to submission.
marketing-copy
Write outbound promotional copy for a product or project: launch and update posts for community platforms and social media, store page descriptions and short blurbs, landing page headlines and calls to action, press-style announcements, and the naming of a product for another language or market. Covers what may be…