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/tradebaas/groundwork/code-reviewnpx skills add Tradebaas/Groundwork --skill code-reviewgit clone --depth 1 https://github.com/Tradebaas/GroundworkWhat 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 | $0.00095 | $0.02464 |
| Opus 5 | $0.00048 | $0.01232 |
| Sonnet 5 | $0.00019 | $0.00493 |
| Haiku 4.5 | $0.00010 | $0.00246 |
Grade A, and why
code-review 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 yesterday.
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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
code-review: fresh eyes on the diff, one axis at a time
Runs before substantial work is committed, after verify has passed. Trivial changes (a typo,
a one-line fix with an obvious cause) skip it; everything with a spec gets it. The subject is
the actual diff about to be committed, not the intention behind it.
Ground rules
- Independent axes, fresh eyes each. Two axes always run (A and B); a third (C) runs only when the diff is security-sensitive, per its own trigger below. If your tool has subagents, give each axis that runs its own subagent with only the inputs named below. Without subagents, run them as sequential passes, re-reading the diff from scratch each time and carrying no conclusions across.
- Skip what tooling already enforces. Formatting, line caps, denylist, secrets and the rest
of
checks/check.mjsplus the stack gates are the machines' job. A finding a gate would have caught means the gates were not run; stop and run them. - Report by severity per axis: blocker, major, minor. The axes are never merged into one ranked list. Each finding names the file and location, states the problem, and proposes the smallest fix.
First: did this diff weaken a gate?
The axes below hand formatting, denylist, secrets and the rest of checks/check.mjs to the
machines. That hand-off holds only while the machines still run at full strength, so this scan
comes first on every review. It is mechanical and needs no fresh eyes: one pass over the diff,
looking for the moves that lower the bar instead of clearing it.
- A test stopped running: deleted, renamed out of what the runner collects, marked skipped or
pending (
.skip,xit,@pytest.mark.skip, a commented-out body), or parked by an.onlythat takes its neighbors with it. - A test stopped asserting: the name survives, but the assertion is gone, softened to a truthiness check, or rewritten to expect whatever the code now produces.
- A threshold moved the easy way: a coverage minimum, a line or size budget, a lint severity dropped to warning, an allowed-failures count raised.
- A check switched off: a rule disabled in config, a strictness flag flipped, an entry
dropped from
checks/config.json, a CI step removed or made non-blocking, a hook shortened,--no-verifyanywhere. - A suppression appeared at the call site:
eslint-disable,@ts-ignore,# noqa,# type: ignoreand their kin.
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.
- yesterday First seen · 158 lines · 95 tokens per session scan A 70ea59dab55d
code-review is a skill published in the GitHub repository Tradebaas/Groundwork (2 stars, last pushed 6d ago), licensed MIT. It adds 95 tokens to every session and 2,464 once invoked, about $0.0005 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
mission-driver
Create roadmaps and mission configs, then drive the mission-driver AI dev-loop engine. mission-driver lives at tools/mission-driver/ — it reads missions/ .json and loops CHECK → REVIEWPLANS → EXECPLANS → DRAFTPLANS → DEEPAUDIT until the roadmap is done or the audit budget is exhausted. Use this skill when the user…
keel-plan
Create or revise PLAN.md — propose the phase DAG (phases · gates · dependencies) from the user's goal, get approval, write the table and regenerate the colored Mermaid diagram from it. Statuses flip at rituals (/keel-handover, /keel-phase-review); post-completion fixes land in the Fix log.
keel-stats
Render the ritual telemetry visually — turns .claude/ritual-log into reports/ritual-stats.md with PLAN.md-style colored Mermaid interval boxes (session/compact boundaries) + a counts table. Answers "which skills/commands/hooks ran, how often, in which interval".
init
Configure an uninitialized project from an approved charter: stack, scripts, identity, optional Git, and verification.
sdd-serve
Serve the SDD Builder's AI request queue: claim requests with sddnextrequest, draft the proposal, answer with sddrespondrequest. Never writes spec files — the user accepts each proposal in the builder. Use when the user asks to attend, serve or listen to the SDD board queue. / Atiende la cola de peticiones del SDD…
review-creative
Audit customer-facing work for UX, accessibility, brand fit, credibility, and generic AI output. Use for design, marketing, document, presentation, or visual review.