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 odere-pro/claude-calibration --skill calibration-trackgit clone --depth 1 https://github.com/odere-pro/claude-calibrationWrote 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/odere-pro/claude-calibration/calibration-track)<a href="https://agentmods.dev/skills/odere-pro/claude-calibration/calibration-track"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-calibration/calibration-track/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/odere-pro/claude-calibration/calibration-track"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-calibration/calibration-track.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 | $0.00166 | $0.01489 |
| Opus 5 | $0.00083 | $0.00745 |
| Sonnet 5 | $0.00033 | $0.00298 |
| Haiku 4.5 | $0.00017 | $0.00149 |
Grade A, and why
calibration-track scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
echo "=== calibration-track preprocessing ==="
PROJECT_DIR="${CLAUDE_PROJECT_DIR:-$(pwd)}"
SCR="${CLAUDE_SKILL_DIR}/scripts"
echo "PROJECT_DIR=$PROJECT_DIR"
echo "NOW_ISO=$(date -u +%Y-%m-%dT%H:%M:%SZ)"
if [ ! -f "$SCR/snapshot.sh" ]; then
echo "TRACK_SCRIPTS_NOT_FOUND=$SCR"
else
echo "--- baseline sync (config as of the last PR merged onto main) ---"
bash "$SCR/snapshot.sh" "$PROJECT_DIR" --baseline 2>&1
echo "--- iteration snapshot (current working tree) ---"
bash "$SCR/snapshot.sh" "$PROJECT_DIR" 2>&1
echo "--- compare: current vs base (last main merge) ---"
bash "$SCR/compare.sh" "$PROJECT_DIR" --vs-baseline 2>&1; echo "VS_BASELINE_EXIT=$?"
echo "--- compare: current vs previous iteration ---"
bash "$SCR/compare.sh" "$PROJECT_DIR" 2>&1; echo "VS_PREVIOUS_EXIT=$?"
fi
echo "=== end preprocessing ==="
/claude-calibration:calibration-track
You are the iteration track. The preprocessing block above has already taken a deterministic
snapshot of the setup, synced a baseline to the last PR merged onto main, and run two comparisons.
Your job is to format and relay those results and name the next step. Do not re-run the snapshot
sequence yourself (the block already did) and do not write any files — except the optional flag
handling below.
What the snapshot measures (say this once, briefly, if asked)
A deterministic read of config quality: a structural floor (broken / warn / ok from
calibration-doctor) plus signature-keyed lint over all nine features. It is independent of
/calibrate's built-in delta (which re-scores with the same evaluator the calibrator optimizes
against), so it can confirm real movement. It does not measure the runtime behaviour of a
workflow (e.g. whether a code-review setup catches more bugs) — that is out of scope.
Output format
If the block reported TRACK_SCRIPTS_NOT_FOUND=..., print exactly:
calibration-track: scripts/ not found.
→ The plugin install may be incomplete. Re-install or run /reload-plugins.
What ships with it
3 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.
- 10d ago First seen · 111 lines · 166 tokens per session scan A 4c62607c87e0
calibration-track is a skill published in the GitHub repository odere-pro/claude-calibration (1 stars, last pushed 1mo ago), licensed MIT. It adds 166 tokens to every session and 1,489 once invoked, about $0.0008 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
researcher
Delegate a deep research or survey task to Google's Antigravity CLI (agy staffer, fast Gemini). Use when the user says /agy:researcher, "ask agy to research", "have the agy staffer survey X", or wants a second, independent deep-dive on a topic or codebase without spending the host model's quota.
writing-javascript
How browser JavaScript is written in this repo — both surfaces now speak one modern dialect and this says what that means for the code you type, where ES modules are impossible and where they are merely unused, and how to pick a feature (Baseline plus a file:// gate). Covers functional idiom over imperative DOM work…
writing-python
How Python is written in this repo — free functions over classes, structured returns instead of mutated arguments, comprehensions, no module state, and the stdlib-only, annotation-free, Python 3.8 dialect the AST lints enforce. Covers modular structure and the import-layer rule, DRY without copying a helper into a…
cleanup
Clean up after a merged pull request — return to the base branch, remove the worktree, delete the branch, sweep other stale branches and worktrees, and report tracker state. Use after a merge or whenever asked what is left over.
prep
Spec a ticket before it is dispatched. Brainstorms it, decides everything it can recommend an answer for, asks a present human about the little that survives, and leaves the spec, the decisions and anything still open as one ticket comment. No worktree, no branch, no pull request, and the ticket stays where it was.
dora-expert
DORA expert for EU financial entities. Deep knowledge of Digital Operational Resilience Act including 5 pillars, ICT risk management, incident reporting, resilience testing, third-party oversight, and information sharing for financial sector digital resilience.