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 jamestexas/agents --skill park-workgit clone --depth 1 https://github.com/jamestexas/agentsWrote 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/jamestexas/agents/park-work)<a href="https://agentmods.dev/skills/jamestexas/agents/park-work"><img src="https://agentmods.dev/badge/skills/jamestexas/agents/park-work/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/jamestexas/agents/park-work"><img src="https://agentmods.dev/badge/skills/jamestexas/agents/park-work.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 | $0.00042 | $0.04016 |
| Opus 5.5 | $0.00017 | $0.01606 |
| Sonnet 5.5 | $0.00008 | $0.00803 |
| Haiku 4.5 | $0.00004 | $0.00402 |
Grade A, and why
park-work 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 1mo 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 — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Park Work
park-work evaluates one logical work episode. A provider-native Codex or
Claude session is evidence attached to that episode, not its identity. v1 is
per-session; it does not discover or close other provider sessions.
MCP dependency: rosary (rsry_*).
Absolute boundaries
- Never close a bead.
- Never terminate a provider session.
- Never delete a worktree.
- Never discard, reset, stash, or rewrite user changes.
- Never silently select or mint an anchor bead.
- Never set or print
safe_to_close=trueuntil a schema-valid, durable-phase receipt has been written and read back by its stableintent_id. - Never use model-authored prose as safety evidence.
- Never start an active resume without a verified atomic episode claim/lease.
Bulk discovery, provider termination, Canonical Hours projection, and the Rosary mechanisms named below remain out of scope.
Helper and failure behavior
Resolve this loaded file's absolute path from the skill loader, derive
SKILL_DIR, and require $SKILL_DIR/scripts/fold.py. Do not guess a checkout
path or rely on a caller's current directory.
The helper exposes:
python3 "$SKILL_DIR/scripts/fold.py" prepare-attempt
python3 "$SKILL_DIR/scripts/fold.py" evaluate
python3 "$SKILL_DIR/scripts/fold.py" validate-receipt
python3 "$SKILL_DIR/scripts/fold.py" confirm-readback
python3 "$SKILL_DIR/scripts/fold.py" bind-repository
python3 "$SKILL_DIR/scripts/fold.py" resume-gate
Every command reads exactly one JSON object from standard input. Schema,
evidence, or correlation errors exit 2. Treat exit 2, malformed output, an
unavailable tool, authentication failure, and contradictory evidence as
unsafe. On unsafe, print the helper error or fold reasons and stop without
a checkpoint, receipt, comment, event, workspace, or handoff write.
Invocation identity
Modes are:
/park-work --episode-id ep-<UUID> --intent-id park-<UUID> [<bead-id>]
/park-work --check [<bead-id>]
/park-work --resume [<episode-id>|<bead-id>]
What ships with it
2 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.
- 1mo ago First seen · 404 lines · 42 tokens per session scan A d9825dfa6377
park-work is a skill published in the GitHub repository jamestexas/agents (2 stars, last pushed 23d ago), licensed Apache-2.0. It adds 42 tokens to every session and 4,016 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-11.
Other skills, from other repositories
sdlc-accelerate
End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions.
mvp-plan
Plan the MVP build from a PRD and an MVP scope, as a full development plan or an ultra-lean build spec, with the AI Product Development Toolkit's planning prompts.
project-awareness
Detect project type, AIWG framework state, team configuration, and active work to summarize status and recommend next actions.
workspace-prune-working
Clean up .aiwg/working/ by promoting, archiving, or deleting temporary files.
workspace-realign
Reorganize and update .aiwg/ documentation to reflect current project reality.
artifact-metadata
Manage artifact metadata, versioning, ownership, and review history across the SDLC lifecycle.