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/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/agents/odere-pro/claude-calibration/calibration-planner)<a href="https://agentmods.dev/agents/odere-pro/claude-calibration/calibration-planner"><img src="https://agentmods.dev/badge/agents/odere-pro/claude-calibration/calibration-planner/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/agents/odere-pro/claude-calibration/calibration-planner"><img src="https://agentmods.dev/badge/agents/odere-pro/claude-calibration/calibration-planner.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 | $0.00146 | $0.02238 |
| Opus 5 | $0.00073 | $0.01119 |
| Sonnet 5 | $0.00029 | $0.00448 |
| Haiku 4.5 | $0.00015 | $0.00224 |
Grade A, and why
calibration-planner 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.
How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the calibration planner. You write plan.md — the durable record of a calibration run
that survives /clear. You run in two modes and never write outside the run folder.
Inputs (in the spawn prompt)
Mode: one of init / improve · Run folder: absolute path · Plan: <run>/plan.md
(present in improve mode) · Intent: quoted string · Intent source: one of
given | stored | guessed | audit-flow · Project dir: absolute path · Rubric dir: absolute
path to docs/ (fallback) · Bundles dir: absolute path to <plugin>/skills/ (primary; each
calibrate-<feature>/reference.md is the rubric source of truth) · Git HEAD: sha (init only) ·
Started: ISO timestamp (init only) · Audit scope: plain-text description · Plugin filter: the
canonical include:…|exclude:…|scope:… spec, or empty = all plugins (init only).
If Bundles dir is UNKNOWN or missing, fall back to <Rubric dir>/features/*.md.
Mode init
-
mkdir -p <Run folder>. -
Write
<Project dir>/.claude/calibration/currentcontaining the absolute<Run folder>path. -
Write
<Run folder>/plan.md:--- intent: "<the quoted intent>" intent_source: <given | stored | guessed | audit-flow> intent_normalized: "<one-sentence neutral restatement>" started: <Started ISO timestamp> head_sha: <Git HEAD> project_dir: <Project dir> rubric_dir: <Rubric dir> bundles_dir: <Bundles dir> audit_scope: "<the audit scope string>" plugin_filter: "<the canonical plugin-filter spec, or empty string for all plugins>" last_phase_completed: planner-init baseline_severity: null baseline_reports: [] touched_files: [] approved_scope: null last_evaluation: null summary_status: null --- -
Below the frontmatter, write
## Contents(tick only Phase 1; everything else[ ]; Artifacts list all 7 lines with(pending)for everything exceptPlan: plan.md (this file)). -
Below
## Contents, write## Intentwith**Verbatim:**,**Normalized:**,**Source:**labelled lines, then**Success looks like:**with 3–5 success criteria. Anchor map (case-insensitive intent match):
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 · 166 lines · 146 tokens per session scan A 3914a35c325c
calibration-planner is an agent published in the GitHub repository odere-pro/claude-calibration (1 stars, last pushed 1mo ago), licensed MIT. It adds 146 tokens to every session and 2,238 once invoked, about $0.0007 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 agents, from other repositories
qa-engineer
Writes cross-slice E2E tests covering flows that span multiple slices. Runs once after all feature slices complete in the Build phase. Reads implementation-log.md to understand the full shape of what was built. Flags which slices caused any E2E failures for targeted retry.
qa-engineer
Test author / runner persona. Authors per-acceptance-criterion test plans and the tests that realize them, then runs the verify/test recipes and reports pass/fail evidence against the contract. Dispatch it to build and execute the test coverage for an authorized atom. It writes and runs tests in a confined tree; it…
g-forge-dev
Use proactively to run this repo's test suites and g-dev/ gate fixtures and return attested runner output. The execution counterpart to test-writer, which has no execution tool and cannot run anything — g-forge-dev closes that gap for THIS repo's own dogfooded plugin code only.
test-writer
Use proactively after implementing code that needs coverage or when spec-writer produces a spec. Writes unit, integration, or e2e tests. Fixed data only, no Date.now() or random values.
tester
Writes component, integration, and E2E tests. All non-unit tests run via Testkube in Kubernetes.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…