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 JetXu-LLM/DocMason --skill workspace-bootstrapgit clone --depth 1 https://github.com/JetXu-LLM/DocMasonWrote 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/jetxu-llm/docmason/workspace-bootstrap)<a href="https://agentmods.dev/skills/jetxu-llm/docmason/workspace-bootstrap"><img src="https://agentmods.dev/badge/skills/jetxu-llm/docmason/workspace-bootstrap.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 | $0.00028 | $0.01752 |
| Opus 5 | $0.00014 | $0.00876 |
| Sonnet 5 | $0.00006 | $0.00350 |
| Haiku 4.5 | $0.00003 | $0.00175 |
Grade A, and why
workspace-bootstrap 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 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.
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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workspace Bootstrap
Use this skill when the task is to make a DocMason workspace ready for use, or when ask has discovered that the workspace is not yet ready for a safe answer path.
This is also the correct first explicit setup workflow when the current agent is not running on the native Codex path and needs to determine whether adapter-specific guidance should be refreshed.
Required Capabilities
- local file access
- shell or command execution
- ability to inspect command output
If the agent cannot perform these capabilities, stop and explain that the environment is not capable enough for the workflow.
Procedure
- Inspect
runtime/bootstrap_state.jsonwhen it exists.- if it already says the current workspace root is ready and
.venvstill exists, do not rerun deep bootstrap work by default - if it belongs to another workspace root, treat that as a moved-repo repair case
- treat
self-containedas the only ordinary ask-time ready environment grade- in practice this means the repo-local steady-state runtime is trusted for ordinary work
- treat
mixedanddegradedas repair-needed states
- if it already says the current workspace root is ready and
- If
.venvis absent ordocmasonis not yet runnable from the repo-local environment, start with:./scripts/bootstrap-workspace.sh --yes- add
--jsonwhen machine-readable output helps - on native Codex ordinary cold starts, treat
./scripts/bootstrap-workspace.sh --yes --jsonas the single governed mutation surface before ask-time workspace work can continue - the launcher should run a capability-aware preflight first, then either continue silently or stop once with a structured
host-access-upgradeboundary - in Codex
Default permissions, the ordinary path should use repo-local bootstrap cache only; it should not probe shared user cache paths first - the launcher should prefer the controlled UV bootstrap asset path for ordinary native cold starts instead of broad local-machine Python scavenging
- the launcher may honor an explicit
DOCMASON_BOOTSTRAP_PYTHONoverride for operator repair, but that is not the ordinary first-run path
- Once the launcher succeeds, prefer the repo-local environment for subsequent commands:
./.venv/bin/python -m docmason doctor --json./.venv/bin/python -m docmason prepare --json --yes- or the
docmasonexecutable installed inside.venv
- Run
docmason doctor --jsonwhen you need a readiness snapshot after launcher completion or on an already prepared workspace. - Run
docmason prepare --json --yeswhen the launcher was not used, or when bootstrap needs an explicit rerun to repair or complete the repo-local environment. - If
preparereports a degraded result, follow the reported next steps and rerun only the necessary deterministic command. - Use
docs/setup/manual-workspace-recovery.mdonly when the launcher orpreparestill cannot finish honestly after the governed automatic path has already had enough access. - If the corpus already contains PPTX, DOCX, or XLSX files and LibreOffice is missing or detected but unusable:
- LibreOffice is required only for an Office-rendering corpus; it is not a universal machine baseline dependency
- on macOS with Homebrew already present, DocMason may use
brew install --cask libreoffice-still - on macOS without Homebrew, DocMason should use the official LibreOffice installer path instead of trying to install Homebrew first
- on macOS, if LibreOffice is already detected but fails the governed smoke probe,
prepare --yesshould treat that as a repair or reinstall case rather than as a fake ready state - on Linux, install LibreOffice with the distro package manager or the official packages, then ensure
sofficeis onPATH
- Run
docmason status --jsonwhen you need to confirm the resulting workspace stage. - Recommend
docmason sync --jsonwhen source files are present and the user needs a usable knowledge base next. - If the current agent ecosystem is a compatibility target such as Claude Code rather than the native Codex path, decide here whether generated adapter guidance is needed.
- Recommend
docmason sync-adapters --jsononly when the current agent ecosystem depends on generated adapter files or those files are missing or stale. - Once
.venvexists, prefer the repo-local interpreter for subsequent repository commands instead of switching back to an arbitrary system Python. - Return the final readiness judgment to the main agent. Do not delegate environment sign-off.
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 First seen · 89 lines · 28 tokens per session scan A 1a93833e335e
workspace-bootstrap is a skill published in the GitHub repository JetXu-LLM/DocMason (135 stars, last pushed 4d ago), licensed Apache-2.0. It adds 28 tokens to every session and 1,752 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 2026-08-30.
Other skills, from other repositories
openkb-deck-neon
A skill for creating a single-file HTML slide deck from content stored in OpenKB, a knowledge-base chat system. It defines a dark, high-tech visual style using neon colors, glow effects, and glass-like panels.
openkb-deck-editorial
A tool for creating a single-file HTML slide presentation from compiled knowledge-base content. Its visual style uses a warm cream background, serif typography, and brick-red accents.
openkb-html-critic
Use to review a generated HTML deck or single-page artifact for visual quality and structural correctness. Especially good at catching CSS specificity bugs where slide-modifier classes (.divider, .center, .q, .flow etc.) accidentally override the base .slide{display:none} and cause one slide to stack on top of every…
transformer-attention
Use when reasoning about Transformer self-attention, multi-head attention, positional encoding, masked decoder attention, or why attention replaced recurrence/convolutions in sequence models; not for generic NLP or unrelated attention topics.
release-sync
Syncs latest release content to NotebookLM and HQ Knowledge Base after version tagging. Reads CHANGELOG, CLAUDE.md, and hook README, updates notebook sources, and ingests release digest. Optionally generates podcast from updated knowledge base. Use after tagging a new version to propagate release knowledge.
openlore
Query and publish to an OpenLore knowledge base over SSH using ordinary shell commands. Use when a task needs project documentation, runbooks, shared team knowledge, or a place to publish findings.