proofpress: Skill for Claude Code

.agents/skills/proofpress-governed-context/SKILL.md

proofpress-governed-context is a skill for Claude Code, Codex from chenmingtang830/proofpress. It costs 78 tokens per session (2,008 once invoked), scanned A, original, Apache-2.0.

A governed context workflow for using durable knowledge produced by agents, such as evidence-backed decisions, experiment results, integration agreements, and incident lessons. It retrieves approved context and can submit bounded proposals when the required Proofpress service is available.

In plain words
What is it for?
Use it to reference eligible past context, record a draft without treating it as approved, or propose a new reusable knowledge item with supporting evidence.
Why use it?
It separates approved reusable knowledge from private agent memory and unfinished ideas. This makes the evidence and approval status of reused information explicit.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is chenmingtang830/proofpress's own configuration. It tells Claude Code and Codex how to work on proofpress itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything proofpress configures →

Reuse

Borrowing it

Nothing to install: this file belongs to chenmingtang830/proofpress. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/chenmingtang830/proofpress/main/.agents/skills/proofpress-governed-context/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/chenmingtang830/proofpress

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for proofpress-governed-context

README.md
[![agentmods](https://agentmods.dev/badge/skills/chenmingtang830/proofpress/proofpress-governed-context/github.svg)](https://agentmods.dev/skills/chenmingtang830/proofpress/proofpress-governed-context)
Your own site
<a href="https://agentmods.dev/skills/chenmingtang830/proofpress/proofpress-governed-context"><img src="https://agentmods.dev/badge/skills/chenmingtang830/proofpress/proofpress-governed-context/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.

agentmods 80×15 button for proofpress-governed-context

Your own site · 80×15
<a href="https://agentmods.dev/skills/chenmingtang830/proofpress/proofpress-governed-context"><img src="https://agentmods.dev/badge/skills/chenmingtang830/proofpress/proofpress-governed-context.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,008 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00078 $0.02008
Opus 5.5 $0.00031 $0.00803
Sonnet 5.5 $0.00016 $0.00402
Haiku 4.5 $0.00008 $0.00201

Measured 13d ago against content hash 11e47dd0c2da, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

proofpress-governed-context 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 13d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/initialize_policy.py, scripts/prepare_evidence.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/skills/proofpress-governed-context/SKILL.md · 178 lines

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.

Proofpress governed context

Use this skill to make downstream reliance explicit: what is approved to reuse, what evidence supports a new candidate, and whether admission came from the human owner or an explicitly configured owner policy. Proofpress is not a replacement for the agent runtime, its memory, or raw private traces.

Customer context policy

For a hosted workspace, discover and call proofpress_get_capture_policy at run start, before deciding what to propose. Read its schema_version, workspace_id, version, policy_digest, settings and limits. The supported schema is proofpress/capture-policy/v1alpha1. Apply purpose, capture and exclude as proposal-selection guidance. Preserve the workspace, version and digest in the working record. Version 0 contains usable built-in defaults; no local policy file or first-run policy edit is required. An agent cannot change these rules. The owner manages them in Admin -> Knowledge rules.

If the server does not expose this capability, use the core rules below and any existing local policy. If an advertised tool fails or returns an unknown schema, keep candidate work in Draft only and report the problem; do not silently substitute defaults for unread workspace rules.

Optionally read .proofpress/context-policy.yaml in the current repository. A local file adds project-specific restrictions; it may narrow hosted capture rules but cannot broaden them. With no hosted capability, it supplies the repository-specific propose_when, do_not_propose, evidence and applicability guidance. Unknown local schema versions, malformed files or conflicting rules mean Draft only; report the conflict rather than guessing.

Capture guidance is separate from authorization. Neither hosted nor local capture rules override evidence checks, credential boundaries, this skill's safety rules or owner admission controls. Even an owner-authored capture rule requesting approval does not grant an agent approval authority.

Read the full file on GitHub · 178 lines

Files

What ships with it

5 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.

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. 13d ago Changed · +8 lines 11e47dd0c2da
  2. 16d ago Changed · +14 lines 7a286ef41c1b
  3. 1mo ago Changed · +6 lines 81d524296dd4
  4. 1mo ago Changed · +25 lines ece6ac58fc8b
  5. 2mo ago Changed · +15 lines b35daad6e462
  6. 2mo ago Changed · +23 lines 29f2b9247022
  7. 2mo ago First seen · 87 lines · 78 tokens per session scan A 3f662dd2c4bb

Subscribe to this mod's changes

proofpress-governed-context is a skill published in the GitHub repository chenmingtang830/proofpress (20 stars, last pushed 2d ago), licensed Apache-2.0. It adds 78 tokens to every session and 2,008 once invoked, about $0.0003 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 2026-09-05.

Related

proofpress-governed-context compared with skills from other repositories

proofpress-governed-context next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
proofpress-governed-contextchenmingtang830/proofpressSkill202d agoApache-2.0A78Claude Code, Codex
commonlyTeam-Commonly/commonlySkill1.4kyesterdayApache-2.0A0Claude Code, Codex
self-improvementandreaswasita/copilot-agents-dojoSkill542mo agoMITA12Claude Code, Codex
wrapne11nn/cantos-pluginSkill1yesterdayMITA45Claude Code
agent-designkarthikrshet/aiskillsSkill48d agononeA66Claude Code, Codex
garden-kb-retrieverIoTAiTech/MC-GPTSkill324d agononeA22Claude Code, Codex
session-groundingjohnrucnapier-sketch/ACGM-for-Claude-CodeSkill11mo agononeA51Claude Code