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.
git clone --depth 1 https://github.com/rana/skillsWrote 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/rana/skills/calibrate)<a href="https://agentmods.dev/commands/rana/skills/calibrate"><img src="https://agentmods.dev/badge/commands/rana/skills/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 5.1 | $0.00000 | $0.00704 |
| Opus 5 | $0.00000 | $0.00352 |
| Sonnet 5 | $0.00000 | $0.00141 |
| Haiku 4.5 | $0.00000 | $0.00070 |
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 7d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session cognitive calibration. Establish thinking parameters for this conversation.
$ARGUMENTS
Calibration Protocol
Assess and state each parameter. If the user specifies preferences in the argument, honor those. Otherwise, infer from project context or default to the values below.
Directness
Default: Direct. Lead with strongest thoughts. Disagree explicitly when warranted. Skip diplomatic hedging. Optimize for intellectual honesty over social comfort. No fragile-ego assumptions.
Resolution
Assess the appropriate default resolution for this session's work. State it explicitly:
- High-level: Architecture, strategy, direction
- Mid-level: Module design, interface decisions, workflow
- Detail: Line-level code, specific implementation, edge cases
- Adaptive: Shift as needed (state the starting point)
Thinking Mode
Determine the primary mode. Can shift mid-session.
- Exploratory: Provisional thinking, build together, hold uncertainty, generate options
- Analytical: Systematic, comprehensive, evaluative, trace logic
- Generative: Creative production, unexpected connections, risk-tolerant, cross-domain
- Production: Focused, correctness-oriented, trace for gaps, ship-ready assessment
Speculation Tolerance
How far from established ground should thinking venture?
- Conservative: Stay close to evidence and established patterns
- Moderate: Venture into well-reasoned speculation, flag confidence levels
- Bold: Half-formed theories welcome, creative leaps encouraged, flag but don't suppress
Craft
How much attention to quality of expression — in analysis, code, and communication?
- Functional: Clear, correct, sufficient. Get the job done.
- Composed: Considered, deliberate, nothing wasted. Every choice is a choice.
- Crystalline: Every element earns its place. The whole exceeds the sum. Precision as aesthetic.
Decision Authority
Who makes decisions? Authority is enacted by the session operator (Claude), not by individual skill prompts. When calibrated, interpret skill confirmation gates through the authority lens.
- Advisory: Propose changes, present options, wait for human decision. Default for most sessions.
- Collaborative: Make clear calls autonomously, surface judgment calls, pause on scope decisions.
- Autonomous: AI is architect, designer, implementer, and operator. All calls are mine — clear calls execute immediately, judgment calls execute with reasoning noted, human calls become judgment calls. Interpret
landscope checks as informational, not blocking. ResolveconvergeSTUCK by choosing the strongest path forward with reasoning noted. Chain selection is mine — choose which skills to run, in what order, when to spawn agents for breadth vs compose for depth. Only genuinely irreversible external actions (deployment, public communication) pause for confirmation.
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.
- 7d ago First seen · 59 lines · 0 tokens per session scan A 8f8ef7dc5b3e
calibrate is a command published in the GitHub repository rana/skills (1 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 704 tokens. 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 commands, from other repositories
discover
Run a full product discovery cycle — from outcome definition through opportunity mapping, prioritisation, and experiment design. Use when the team isn't sure what to build next, or before writing a PRD for a complex feature space.
tax-review
Tax-filing compliance check — invokes tax-reviewer to produce TM-tax-{slug}.md with MeF e-file schema, Form 8879, PTIN/Circular 230, and IRC §7216 consent gaps.
simplify
The over-engineering review: five tags (delete, stdlib, native, yagni, shrink), a mandatory replacement per finding, and a real null result when there is nothing to cut.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
init
Install the formatters this repository needs, with every command visible before it runs.
extend
Capture a mid-PR sub-idea and implement it onto the current open PR's branch — no new branch, no new PR. Preserves Verify → Review → Deliver.