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/JordanGrothentic/caliberWrote 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/jordangrothentic/caliber/which-effort)<a href="https://agentmods.dev/commands/jordangrothentic/caliber/which-effort"><img src="https://agentmods.dev/badge/commands/jordangrothentic/caliber/which-effort.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 | $0.00042 | $0.00288 |
| Opus 5 | $0.00021 | $0.00144 |
| Sonnet 5 | $0.00008 | $0.00058 |
| Haiku 4.5 | $0.00004 | $0.00029 |
Grade A, and why
which-effort 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 8d 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.
What it actually says
Locate the caliber skill files, trying these locations in order: the project
.claude/skills/caliber/, then ~/.claude/skills/caliber/, then a Glob for
**/skills/caliber/SKILL.md. Read SKILL.md and models.md from the first location
that has them. If they cannot be found, stop and tell the user the caliber skill is
not installed (copy skills/caliber from the repo into ~/.claude/skills/ or the
project .claude/skills/), and never recommend models, efforts, or prices from
memory.
Apply the engine to the task below and produce the effort only ladder exactly as the
skill's Entry points section defines for /which-effort; the engine is authoritative.
Choose the model to ladder on in this order, and always name which one you used: a
model named in the task text, else the session's current model (you know which model
you are running as), else the Optimal pick.
Task: $ARGUMENTS
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.
- 8d ago First seen · 21 lines · 42 tokens per session scan A b6ed16a1bb79
which-effort is a command published in the GitHub repository JordanGrothentic/caliber (4 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 288 once invoked, about $0.0002 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 commands, from other repositories
pr
Create a pull request using the git-pushing skill.
bugfix
IMPORTANT: You MUST run this shell command FIRST before doing anything else.
feature
IMPORTANT: You MUST run this shell command FIRST before doing anything else.
refactor
IMPORTANT: You MUST run this shell command FIRST before doing anything else.
atomic-plan
Write a design doc (concepts, business rules, approaches) and a checkpoint-table spec (contract) for non-trivial work; inline spec only for trivial. Gauges triviality; loops spec authoring with subagents. Human-facing artifact, Mermaid diagrams allowed.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.