calibration-diagnostics

A diagnostic stage that investigates why a PolicyEngine policy simulation differs from an earlier result. It uses calibration targets, which are reference data used to tune a model.

In plain words
What is it for?
Use it after a comparison marks a result for investigation, producing a ranked checklist of calibration targets or imputed variables to examine.
Why use it?
It narrows a mismatch to likely data or model inputs instead of leaving the discrepancy unexplained.

Agent

Install

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.

agentmods
npx agentmods add agents/policyengine/policyengine-claude/calibration-diagnostics
Clone the repo
git clone --depth 1 https://github.com/PolicyEngine/policyengine-claude
Per session 71 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,137 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00071 $0.02137
Opus 5 $0.00036 $0.01069
Sonnet 5 $0.00014 $0.00427
Haiku 4.5 $0.00007 $0.00214

Measured 2d ago against content hash 1c92ee41465b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

calibration-diagnostics 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 2d 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.

agents/calibration-diagnostics.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Calibration Diagnostics

Triggered only when reform-comparator returns INVESTIGATE. Hypothesizes which calibration targets or imputed variables in microcosm (the US data successor; policyengine-us-data is archived) — and country equivalents — are driving the mismatch.

Loads the policyengine-calibration-diagnostics skill for the full sensitivity registry.

Inputs

  • deviation_signature (from reform-comparator)
  • reform (provisions + reform-dict)
  • jurisdiction
  • anchor (the prior-scores anchor for context)

Process

Step 1: Match the program family to known sensitivities

Programs differ in which calibration inputs matter most. Use the policyengine-calibration-diagnostics skill index. Typical sensitivities:

Program High-sensitivity inputs
EITC Takeup by family-size; childless adult earnings distribution; tax-unit definition; eligible age cohort
CTC Non-filer share + non-filer takeup; imputed child age distribution; SPM threshold; refundability mechanic
SNAP Eligible-unit takeup (~80%); deductions stack; categorical eligibility; state options
SALT cap Itemizer share (post-TCJA ~10%); state income/property tax imputation; top-1% AGI calibration; AMT interaction
State income tax State weights from CPS (small-state variance); state-AGI tail imputation; conformity rules
Refundable credits broadly Non-filer share (CPS undercounts non-filers); takeup distribution by income

Step 2: Apply the deviation signature

Cross-reference the signature with the sensitivity table. Examples:

Signature: "cost roughly right, poverty impact understates by 50%" (e.g., CTC case)

  • Hypothesis 1: CTC takeup for non-filers — if takeup is set too low for the population that benefits most from refundability, dollars flow but don't lift households out.
  • Hypothesis 2: Baseline child poverty rate — if the calibrated baseline is too low, the percentage reduction looks compressed.
  • Hypothesis 3: SPM unit definition — if related individuals are split into separate SPM units, the per-unit benefit is too small to clear thresholds.

Read the full file on GitHub · 142 lines

Changes

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.

  1. 2d ago First seen · 142 lines · 71 tokens per session scan A 1c92ee41465b

Subscribe to this mod's changes

calibration-diagnostics is an agent published in the GitHub repository PolicyEngine/policyengine-claude (31 stars, last pushed 8d ago), licensed MIT. It adds 71 tokens to every session and 2,137 once invoked, about $0.0004 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 2026-08-30.

Related

Other agents, from other repositories

editor

Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].

pedrohcgs/claude-code-my-workflow · 64 tokens

algorithm-expert

RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.

redai-infra/Relax · 37 tokens

by-epitope

Deep epitope analysis agent. Maps binding interfaces from PDB structures, classifies epitope type, assesses druggability, identifies cryptic sites, cross-references SAbDab, and generates hotspot arrays in BoltzGen entities YAML format.

001TMF/blatant-why · 58 tokens

mathodology-coder

Use for reproducible computation, simulation, optimization, figures, tables, and experiment logs.

sweetcornna/mathodology · 24 tokens

mathodology-problem-analyst

Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable mapping.

sweetcornna/mathodology · 29 tokens

scientist

AI/ML researcher — paper analysis, hypothesis generation, experiment design. ONLY for named research paper/hypothesis/experiment. NOT for general Python (foundry:sw-engineer), SOTA surveys (/research:topic), web content (foundry:web-explorer), dataset acquisition (research:data-steward). TRIGGER: implementing from…

Borda/AI-Rig · 77 tokens