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/chenmingtang830/proofpress/proofpress-governed-contextnpx skills add chenmingtang830/proofpress --skill proofpress-governed-contextgit clone --depth 1 https://github.com/chenmingtang830/proofpressWrote 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/chenmingtang830/proofpress/proofpress-governed-context)<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="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 5.1 | $0.00078 | $0.00870 |
| Opus 5 | $0.00039 | $0.00435 |
| Sonnet 5 | $0.00016 | $0.00174 |
| Haiku 4.5 | $0.00008 | $0.00087 |
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 today.
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 — 87 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 eligible to reuse, what evidence supports a new candidate, and which authorized human must approve it. Proofpress is not a replacement for the agent runtime, its memory, or raw private traces.
Preconditions
Require a configured Proofpress MCP server or a supported Python, CLI, or HTTP client with an agent-scoped token. Use the configured review base URL when one is available. Do not request, copy, print, or store owner or recovery credentials.
If the client cannot reach Proofpress or cannot authenticate, continue the primary task without claiming governed reuse or proposal submission. Report the missing integration as a blocker; do not silently substitute local memory as approved context.
Decide the action
Choose exactly one mode for each knowledge-bearing outcome:
- Reference only — retrieve eligible, in-scope governed context before relying on it; state its scope and any limits in the task result.
- Draft only — keep a working hypothesis or incomplete finding in the task output; do not submit it as a reusable candidate.
- Propose — submit a bounded candidate when the task produces a durable decision, evidence-backed conclusion, reproducible experiment result, integration contract, or incident learning that a later agent or person could rely on.
Do not propose routine code edits, an unverified debugging theory, duplicated context, broad raw traces, credentials, or a claim whose scope cannot be stated. When the user explicitly asks to propose, submit the candidate if the evidence and scope are sufficient; otherwise explain what is missing.
Reference governed context
- Discover the configured capability surface first. For MCP, inspect its tools and use context or graph retrieval. For CLI, SDK, or HTTP, use the matching context operation rather than inventing an endpoint.
- Query the narrowest useful scope. Treat only results explicitly marked eligible for reuse as inherited knowledge.
- Preserve the result's identifier, scope, status, evidence limits, and supersession or conflict state in the working record. A previous proposal, rejected candidate, expired item, or unresolved conflict is not reusable context.
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.
- today First seen · 87 lines · 78 tokens per session scan A 3f662dd2c4bb
proofpress-governed-context is a skill published in the GitHub repository chenmingtang830/proofpress (5 stars, last pushed today), licensed Apache-2.0. It adds 78 tokens to every session and 870 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 2026-09-05.
Other skills, from other repositories
memory-forest
Build, validate, index, and query a private local Memory Forest with provenance-aware layers, pointer-first search, and validated root-first retrieval. Use when creating a new forest, checking an existing forest's structure, building its local SQLite index, or retrieving bounded memory trails without exposing full…
memory-forest-retrieve
Integrate a mandatory, metadata-only Memory Forest consultation gate before an agent responds to each non-empty user-authored text turn.
okf
Author, maintain, and consume Open Knowledge Format (OKF) knowledge bundles — portable markdown + YAML frontmatter that both humans and agents read. Use when capturing project knowledge (services, APIs, schemas, metrics, runbooks, decisions) into an OKF bundle, when updating one after code or docs change, or when a…
setup
Scaffold a complete knowledge system. Detects platform, conducts conversation, derives configuration, generates everything. Validates against 15 kernel primitives. Triggers on "/setup", "/setup --advanced", "set up my knowledge system", "create my vault".
rethink
Challenge system assumptions against accumulated evidence. Triages observations and tensions, detects patterns, generates proposals. The scientific method applied to knowledge systems. Triggers on "/rethink", "review observations", "challenge assumptions", "what have I learned".
architect
Research-backed evolution advice for your knowledge system. Analyzes health reports, friction patterns, and derivation history to propose specific changes with research justification. Never auto-implements — proposals require your approval.