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 agentmods add skills/policyengine/policyengine-claude/encode-policy-v2npx skills add PolicyEngine/policyengine-claude --skill encode-policy-v2git 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/encode-policy-v2)<a href="https://agentmods.dev/skills/policyengine/policyengine-claude/encode-policy-v2"><img src="https://agentmods.dev/badge/skills/policyengine/policyengine-claude/encode-policy-v2.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 | $0.00075 | $0.00618 |
| Opus 5 | $0.00037 | $0.00309 |
| Sonnet 5 | $0.00015 | $0.00124 |
| Haiku 4.5 | $0.00007 | $0.00062 |
Grade A, and why
encode-policy-v2 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 4d 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
encode-policy-v2
Thin launcher. The canonical workflow—routing, arguments, phases, roles, checkpoints, artifact contracts, retry budgets, and completion gates—lives in references/workflow.md. Read it completely before acting and follow it exactly; do not redefine or compress its behavior here.
Treat the text after $encode-policy-v2 as raw workflow arguments:
$encode-policy-v2 STATE PROGRAM [--skip-review] [--research-only] [--600dpi]
[--resume] [--from-phase N] [--full-validation]
Mandatory gates that no surface may skip:
- Route purely parametric changes to
encode-reformunless the user chooses to continue. - Make no GitHub write before the user-approved scope decision exists.
- Render every page of every collected PDF; extracted text is not a substitute.
- Do not push through a red structural or quick-audit gate, or silently push failing tests.
- Keep the PR draft and complete the required follow-up review after any review-fix round.
- Do not finish before the Phase 7 summary and canonical completion contract are satisfied.
Surface adapters:
- Claude Code: also read references/claude-launcher.md, which maps canonical roles and abstract operations to Claude Code mechanics.
- Codex: use the delegation mapping below.
Codex delegation mapping, when subagent use is available and authorized:
- Use
workerfor every role that writes repository files, runtime artifacts, reports, GitHub state, or Git state. Useexploreronly for bounded read-only discovery or audit questions whose result can be returned directly without writing an artifact. - Preserve canonical dependencies. Run independent review-fixer-vars and review-fixer-tests roles concurrently; keep implementation, validation, and push roles in canonical order.
- Pass concrete
WORKTREE_ROOT,WORKTREE_ID,RUN_ROOT, andPREFIXvalues, the role's full canonical task contract, owned paths, required outputs, and named PolicyEngine skills to every subagent. Do not assume child agents inherit parent skill context. - Remind every implementation subagent that other agents may share the worktree, it must not revert unrelated edits, and only the canonical pusher roles may commit or push.
- If subagents are unavailable or not authorized, execute roles directly in phase order while preserving the same ownership, handoff files, user checkpoints, and gates.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 53 lines · 75 tokens per session scan A 6bbec595ff85
encode-policy-v2 is a skill published in the GitHub repository PolicyEngine/policyengine-claude (32 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 618 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.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.