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.
npx skills add PolicyEngine/policyengine-claude --skill policyengine-calibration-diagnosticsgit clone --depth 1 https://github.com/PolicyEngine/policyengine-claudeWrote 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/skills/policyengine/policyengine-claude/policyengine-calibration-diagnostics)<a href="https://agentmods.dev/skills/policyengine/policyengine-claude/policyengine-calibration-diagnostics"><img src="https://agentmods.dev/badge/skills/policyengine/policyengine-claude/policyengine-calibration-diagnostics/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/skills/policyengine/policyengine-claude/policyengine-calibration-diagnostics"><img src="https://agentmods.dev/badge/skills/policyengine/policyengine-claude/policyengine-calibration-diagnostics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00182 | $0.02719 |
| Opus 5.5 | $0.00073 | $0.01088 |
| Sonnet 5.5 | $0.00036 | $0.00544 |
| Haiku 4.5 | $0.00018 | $0.00272 |
Grade A, and why
policyengine-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.
How it starts
The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PolicyEngine calibration diagnostics
Converts tribal "I'd check the takeup rate first" knowledge into a structured sensitivity
registry, and pairs it with the live per-target calibration API so hypotheses are ranked against
real relative_error numbers rather than assumptions. When an /analyze-policy comparison
returns INVESTIGATE, this skill supplies the ranked candidate causes.
The calibrated microdata is now a Microcosm build (see the policyengine-data skill for how
targets, weights and opt-in L0 pruning work, and where the US default's households come from).
Calibration targets live in the Microcosm build's target set — not in a hand-maintained loss
file — and their fit is queryable per release from the dashboard API below.
When to use
- Stage 5.6 / Stage 6 of
/analyze-policy— invoked by thecalibration-diagnosticsagent. - Code review of microsim PRs where the headline number differs from priors.
- Designing or auditing a Microcosm calibration target.
- Debugging why a state-level run looks volatile.
Top-level architecture
PolicyEngine microsim results depend on three layers:
- Country model logic (policyengine-us, policyengine-uk, policyengine-canada) — formulas, parameters.
- Calibrated microdata (Microcosm) — survey weights + imputations matched to administrative targets.
- Behavioral assumptions (takeup rates, labor-supply elasticities) — usually parameters but easy to overlook.
A magnitude mismatch is almost always rooted in layer 2 or 3, not layer 1 (layer-1 mismatches show up as outright simulation errors, not magnitude drift).
Live calibration API (check this first)
Per-target fit for the current Microcosm release, no auth, reads the release from Hugging Face:
BASE = https://calibration-diagnostics.vercel.app/calibration/dashboard/api/microcosm
GET {BASE}/target-diagnostics?source=<source> # every target for a source, with relative_error
GET {BASE}/target-investigation?target=<id> # full investigation packet for one target
GET {BASE}/releases # release ids for pinning
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.
- 2d ago Changed · +1 lines · -6 tokens per session 59d31923b12d
- 2mo ago First seen · 177 lines · 188 tokens per session scan A a55216268497
policyengine-calibration-diagnostics is a skill published in the GitHub repository PolicyEngine/policyengine-claude (31 stars, last pushed yesterday), licensed MIT. It adds 182 tokens to every session and 2,719 once invoked, about $0.0007 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.
policyengine-calibration-diagnostics compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| policyengine-calibration-diagnosticsPolicyEngine/policyengine-claude | Skill | 31 | yesterday | MIT | A | 182 | Claude Code |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | 3d ago | Apache-2.0 | A | 123 | Claude Code |
| matlabK-Dense-AI/scientific-agent-skills | Skill | 57k | today | MIT | A | 44 | Claude Code |
| exploratory-data-analysisK-Dense-AI/scientific-agent-skills | Skill | 57k | today | MIT | A | 83 | Claude Code |
| phylogeneticsK-Dense-AI/scientific-agent-skills | Skill | 57k | today | MIT | A | 71 | Claude Code, Codex |
| research-engineerdavila7/claude-code-templates | Skill | 33k | today | MIT | A | 43 | Claude Code, Codex |
| mapping-to-snomedmaziyarpanahi/openmed | Skill | 5.8k | today | Apache-2.0 | A | 205 | Claude Code |