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/checkpointnpx skills add Tradebaas/Groundwork --skill checkpointgit 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 | $0.00110 | $0.01444 |
| Opus 5 | $0.00055 | $0.00722 |
| Sonnet 5 | $0.00022 | $0.00289 |
| Haiku 4.5 | $0.00011 | $0.00144 |
Grade A, and why
checkpoint 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
checkpoint: reset the context, keep the thread
Long sessions get expensive: every turn re-sends the whole history. A checkpoint writes down
just enough for a fresh session to pick up exactly where this one stopped, so you can clear the
context (/clear in Claude Code; every tool has its own fresh-session command) and continue at
a fraction of the token cost. The fresh session already reads STATE.md first
(AGENTS.md session protocol, step 1), so the handoff has one home: STATE.md. Do not create a
second document.
This is the light sibling of handover. handover transfers the project to a stranger at a
milestone and runs a full audit. checkpoint just parks the current train of work so you can
resume it yourself in a clean session. If the work is actually being handed to someone else or a
milestone is closing, use handover instead.
When to fire
- Roughly 15% of the context window is spent in this session, or the session is long and every turn feels heavy. Fire before the harness auto-summarizes, so the handoff is yours and accurate, not a lossy machine summary.
- The user asks for it, or is about to clear the context.
- Do not fire for a two-message session: there is nothing to save and the checkpoint itself costs tokens.
The 15% mark is the activation point: propose the checkpoint there by default. Stretching past it to at most ~40% is the user's call, and only when finishing the current unit of work first is clearly better than parking it. Past ~40%, always checkpoint: advise it urgently, before quality degrades and the handoff turns lossy. Suggest, do not force, and never clear the context on the user's behalf. A tool that supports lifecycle hooks can surface this reminder automatically once context crosses the threshold; such a hook only ever suggests.
The method (do it from context you already have; do not re-read the repo)
The whole point is to spend few tokens. Write from what is already in this conversation. Only open a file if a fact is genuinely missing.
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 · 93 lines · 0 tokens per session scan A 4b1794248620
checkpoint is a skill published in the GitHub repository Tradebaas/Groundwork (2 stars, last pushed 6d ago), licensed MIT. It adds 110 tokens to every session and 1,444 once invoked, about $0.0006 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.