aget-document-finding

aget-document-finding is a skill for Claude Code, Codex from aget-framework/aget. It costs 10 tokens per session (599 once invoked), scanned A, original, Apache-2.0.

A structure for recording research findings with supporting evidence, methods, implications, and limitations. It is intended for turning observations into documents that others can review and reproduce.

In plain words
What is it for?
Use it to document a specific finding, list primary sources and observations, explain the reasoning, describe how the result was obtained, and record recommended next steps.
Why use it?
It prevents research conclusions from being separated from the evidence or the process that produced them. Stating limitations also makes uncertainty and missing information visible.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/aget-framework/aget/aget-document-finding
Any agent
npx skills add aget-framework/aget --skill aget-document-finding
Clone the repo
git clone --depth 1 https://github.com/aget-framework/aget

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 aget-document-finding

README.md
[![agentmods](https://agentmods.dev/badge/skills/aget-framework/aget/aget-document-finding.svg)](https://agentmods.dev/skills/aget-framework/aget/aget-document-finding)
Your own site
<a href="https://agentmods.dev/skills/aget-framework/aget/aget-document-finding"><img src="https://agentmods.dev/badge/skills/aget-framework/aget/aget-document-finding.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 599 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00010 $0.00599
Opus 5 $0.00005 $0.00300
Sonnet 5 $0.00002 $0.00120
Haiku 4.5 $0.00001 $0.00060

Measured 3d ago against content hash 9b028ca41e09, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aget-document-finding 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 3d 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.

.claude/skills/aget-document-finding/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

aget-document-finding

Document research findings with evidence, methodology, and implications. Creates structured finding documents for knowledge capture.

Instructions

When this skill is invoked:

  1. Formulate Finding

    • Clear, specific statement
    • Falsifiable where possible
    • Scoped appropriately
  2. Document Evidence

    • Primary sources
    • Data/observations
    • Chain of reasoning
  3. Describe Methodology

    • How finding was reached
    • Tools/techniques used
    • Reproducibility notes
  4. Articulate Implications

    • What this means
    • Recommended actions
    • Future research directions
  5. Note Limitations

    • Scope boundaries
    • Confidence level
    • Known gaps

Output Format

# Research Finding: [Title]

**Date**: [YYYY-MM-DD]
**Researcher**: [Agent Name]
**Status**: [Draft/Reviewed/Accepted]
**Confidence**: [High/Medium/Low]

---

## Finding Statement

[Clear, specific, falsifiable statement of what was discovered]

---

## Evidence

### Primary Sources
1. [Source 1]: [What it shows]
2. [Source 2]: [What it shows]

### Data/Observations
- [Observation 1]
- [Observation 2]

### Reasoning Chain
1. [Premise 1]
2. [Premise 2]
3. Therefore: [Conclusion]

---

## Methodology

**Approach**: [Description of method]

**Tools Used**:
- [Tool 1]
- [Tool 2]

**Reproducibility**: [How to reproduce this finding]

---

## Implications

### Immediate
- [Implication 1]

### Strategic
- [Longer-term implication]

### Recommended Actions
1. [Action 1]
2. [Action 2]

---

## Limitations

1. [Limitation 1]: [How it affects conclusions]
2. [Limitation 2]: [How it affects conclusions]

---

## Future Research

- [Question raised by this finding]

---

## References

1. [Citation 1]

Constraints

  • C1: NEVER document findings without evidence — findings must be supported
  • C2: NEVER overstate confidence level — epistemic humility required
  • C3: NEVER omit contradictory evidence — complete picture enables sound judgment

Read the full file on GitHub · 134 lines

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. 3d ago First seen · 134 lines · 10 tokens per session scan A 9b028ca41e09

Subscribe to this mod's changes

aget-document-finding is a skill published in the GitHub repository aget-framework/aget (11 stars, last pushed 3d ago), licensed Apache-2.0. It adds 10 tokens to every session and 599 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

aget-create-briefing

Generate standalone narrative documents from session artifacts, optimized for a target consumption medium (NotebookLM, slides, memo, share-draft). Use when the user says "create briefing", "create a briefing for NotebookLM", "make this listenable", "summarize session for [medium]", "prepare a listen", "brief me on…

aget-framework/template-advisor-aget · 85 tokens

aget-check-kb

Validate Knowledge Base health by checking structure, frontmatter compliance, and content staleness. Returns conformance score and health status (OK/WARN/CRITICAL).

aget-framework/template-advisor-aget · 38 tokens

markitdown

Convert documents (PDF, Word, Excel, PowerPoint, images) to Markdown text for LLM processing.

markus-global/markus · 25 tokens

context-document

Use when the user says "create context", "document this area", or wants a structured snapshot of a codebase area for agent orientation.

event4u-app/agent-config · 31 tokens

canvas-design

Use when creating static visual art — posters, marketing visuals, brand assets, PDF/PNG design pieces — even if the user just says 'design a poster' or 'mach uns ein Visual'.

event4u-app/agent-config · 42 tokens

aget-close-project

Close a PROJECTPLAN with verifiable-assertion gate (V-tests + commits + retrospective), deferred-surface scan for next-plan handoff, and status transition (ACTIVE → COMPLETE / CLOSED / ABANDONED / SUPERSEDED). Strict counterpart to /aget-create-project (D71 Layer 2). Closes asymmetric verb-pair gap at PROJECTPLAN…

aget-framework/template-advisor-aget · 78 tokens