Borrowing it
Nothing to install: this file belongs to l3lackcurtains/trading-ops. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/l3lackcurtains/trading-ops/main/.claude/commands/calibrate.mdgit clone --depth 1 https://github.com/l3lackcurtains/trading-opsWrote 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/commands/l3lackcurtains/trading-ops/calibrate)<a href="https://agentmods.dev/commands/l3lackcurtains/trading-ops/calibrate"><img src="https://agentmods.dev/badge/commands/l3lackcurtains/trading-ops/calibrate/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/commands/l3lackcurtains/trading-ops/calibrate"><img src="https://agentmods.dev/badge/commands/l3lackcurtains/trading-ops/calibrate.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 | $0.00034 | $0.02748 |
| Opus 5.5 | $0.00014 | $0.01099 |
| Sonnet 5.5 | $0.00007 | $0.00550 |
| Haiku 4.5 | $0.00003 | $0.00275 |
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 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/calibrate — protocol-vs-framework alignment audit
/calibrate is the integrity check between the framework knowledge base (docs/) and the protocol that applies it (guide/ + .claude/commands/). It detects drift, proposes corrective edits to the protocol, and waits for consent. It never edits docs/ — docs/ is canonical and the only writer is /ingest.
The discipline: don't deviate from the KB. The framework grows through /ingest; the protocol stays aligned through /calibrate.
Direction of authority
| Source of truth | Audited target |
|---|---|
docs/ (framework) |
guide/scan/*.md + guide/discover-rules.md + .claude/commands/*.md |
When docs/ and guide/ disagree, docs/ always wins. guide/ is amended to match — never the reverse.
If /calibrate finds a guide/ reference to something that doesn't exist in docs/, that's a flag — either the protocol invented something the framework hasn't sanctioned (remove from guide/), or the framework is genuinely missing a concept (route to /ingest).
Argument forms
| Form | Example | Behavior |
|---|---|---|
| No args | /calibrate |
Full audit across all of docs/ + guide/ + .claude/commands/ |
| Doc-scoped | /calibrate macro.md |
Audit only the protocol surfaces touched by docs/macro.md |
| Concept-scoped | /calibrate "regime quadrant" |
Audit a specific term/concept's usage consistency across the protocol |
All forms are interactive: surface the drift report → wait for consent → apply only the approved fixes.
Steps
Step 1 — Read scope
- Read every
docs/*.mdfile in scope (full content, not just headings) - Read every
guide/scan/*.md,guide/discover-rules.md,guide/scan-rules.md - Read every
.claude/commands/*.md - Read
docs/INGEST_LOG.md— recent ingest events tell you what should have been recalibrated and may have been missed - Read
guide/CALIBRATION_LOG.md— what the last calibration found / fixed / deferred
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 · 206 lines · 34 tokens per session scan A 53b0e3b2da31
calibrate is a command published in the GitHub repository l3lackcurtains/trading-ops (57 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 2,748 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
execute-entry
Execute a new MEICAgent iron condor entry. Only invoke when the entry decision (Step 6) is yes.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.