Skip to content
Agentmart
Submit a tool

evidence-packaging

Package completed bounded execution output into one evidence claim with identity, observations, limitations, and receipt.

Skill by linjuhon

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/linjuhon-evidence-packaging

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Package completed bounded execution output into one evidence claim with identity, observations, limitations, and receipt. Use after an active gate step finishes and before adjudication or state projection.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/evidence-packaging

What's inside

Skill name
evidence-packaging
Description
Package completed bounded execution output into one evidence claim with identity, observations, limitations, and receipt. Use after an active gate step finishes and before adjudication or state projection.
License
MIT
Instructions
44 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# evidence-packaging

Use this skill when a bounded execution step is finished and raw output must become a grounded evidence package.

## Responsibilities

- turn command output, logs, receipts, and artifacts into one claim package
- keep source identity explicit
- keep observations concrete
- keep limitations explicit
- keep supersession explicit

## Required Output

- claim
- source identity
- observations
- limitations
- supersedes / next action

## Hard Rules

- One package proves one claim.
- Do not mix unrelated gates or artifact tuples.
- Do not promote observation to truth without adjudication.
- Do not write a package before the execute step is done.

## Typical Inputs

- active gate card
- current plan pointer
- command output
- runtime logs
- binary hashes
- compare dumps

## Entry And Return

Before writing, read `docs/fa4_plan/CURRENT_PLAN`, `docs/fa4_plan/PLANS.md`,
the active gate card, and `docs/fa4_plan/20_evidence/README.md`. Return the
package path, receipt path if created, exact claim, and the next adjudication
action. Do not update gate status from this skill alone.

From linjuhon/codex-personal-skills, MIT.

More from linjuhon/codex-personal-skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 8, 2026 (2 months ago)
Last release
Aug 8, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/linjuhon/codex-personal-skills
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from linjuhon

Cite this page

evidence-packaging skill. Agent Mart. https://agentmart.dev/skills/linjuhon-evidence-packaging (last updated 2026-10-24)