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/calibratenpx skills add Tradebaas/Groundwork --skill calibrategit clone --depth 1 https://github.com/Tradebaas/GroundworkWrote 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/tradebaas/groundwork/calibrate)<a href="https://agentmods.dev/skills/tradebaas/groundwork/calibrate"><img src="https://agentmods.dev/badge/skills/tradebaas/groundwork/calibrate.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 | $0.00105 | $0.01145 |
| Opus 5 | $0.00053 | $0.00573 |
| Sonnet 5 | $0.00021 | $0.00229 |
| Haiku 4.5 | $0.00011 | $0.00114 |
Grade A, and why
calibrate 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 3d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
calibrate: right-size the model and effort before the session starts
Every session runs on one model at one effort level, and that choice is made once, at the start. The prompt cache is scoped per model: switch mid-session and the entire conversation is re-read at full input price. So the calibration moment is before the work, ideally as a cheap throwaway question in a small-model session, and the output is a start command the user pastes.
This skill carries a method, not a model table. Model names, prices and effort levels change; a hardcoded table would rot. What the session's tool offers today is looked up live, every time.
The method
-
Name the session's work. One ticket per session (AGENTS.md efficiency rule), so the ticket defines the work. If the user hasn't said what the session is for, ask that one question first; without it there is nothing to calibrate against.
-
Get the live lineup, never from memory and never from a saved URL. First establish which tool the session will run in and which vendor's models it offers; that pair is the input, not an assumption. Model names, prices, effort levels and the pages that document them all change over time, so this skill deliberately hardcodes none of them. Search the web for that vendor's official, current documentation at the moment of asking (the models overview with pricing, plus whatever the vendor calls its reasoning dial: effort, extended thinking, reasoning budget) and accept only the vendor's own domains as sources. Cross-check against what the tool itself offers (its model picker or settings). Any model or effort level released after this skill was written is in scope automatically; that is the point of looking it up.
-
Classify the work into a capability tier. Tiers, not model names, so the mapping survives every release:
- Mechanical: doc edits, renames, config changes, running checks, fixes with a known cause. → cheapest current model, low or medium effort.
- Standard build: a spec'd feature, tests, a refactor inside one module, routine review. → the mid-tier all-rounder, its default effort.
- Hard: architecture, debugging with unknown cause, security-sensitive work, ambiguous scope, work where a wrong answer is expensive. → the most capable tier, high effort. Map each tier to the concrete cheapest model that fills it in today's lineup from step 2.
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.
- 3d ago First seen · 76 lines · 105 tokens per session scan A d45ff88db708
calibrate is a skill published in the GitHub repository Tradebaas/Groundwork (2 stars, last pushed 8d ago), licensed MIT. It adds 105 tokens to every session and 1,145 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".
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…
init
Configure an uninitialized project from an approved charter: stack, scripts, identity, optional Git, and verification.
sdd-workflow
Guide a project with Spec-Driven Development (SDD) discipline - idea, approved spec, consistent plan, tasks, a gate that verifies approval and consent, implementation, validation, and logbook. Bilingual EN/ES. Use when the user wants to start, spec, plan, implement, or validate work with SDD, or mentions specs, plans…