aget: Skill for Claude Code

.claude/skills/aget-record-observation/SKILL.md

aget-record-observation is a skill for Claude Code from aget-framework/aget. It costs 42 tokens per session (1,213 once invoked), scanned A, original, Apache-2.0.

A skill for recording research observations in the AGET knowledge base without committing formal specifications. It can capture vocabulary candidates, research-question proposals, web findings, patterns, and other useful notes during a session.

In plain words
What is it for?
Use it to record individual findings, scan a session for observations, or capture the most valuable signals within a time budget.
Why use it?
It preserves useful discoveries before they are forgotten or turned into a specification prematurely.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is aget-framework/aget's own configuration. It tells Claude Code how to work on aget 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 aget configures →

Reuse

Borrowing it

Nothing to install: this file belongs to aget-framework/aget. 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/aget-framework/aget/main/.claude/skills/aget-record-observation/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/aget-framework/aget

Made for: Claude Code.

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-record-observation

README.md
[![agentmods](https://agentmods.dev/badge/skills/aget-framework/aget/aget-record-observation.svg)](https://agentmods.dev/skills/aget-framework/aget/aget-record-observation)
Your own site
<a href="https://agentmods.dev/skills/aget-framework/aget/aget-record-observation"><img src="https://agentmods.dev/badge/skills/aget-framework/aget/aget-record-observation.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,213 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00042 $0.01213
Opus 5 $0.00021 $0.00607
Sonnet 5 $0.00008 $0.00243
Haiku 4.5 $0.00004 $0.00121

Measured 8d ago against content hash ce2bbe98f535, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

aget-record-observation 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 8d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/skills/aget-record-observation/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Record Protocol (v2 - Autonomous-Explicit Continuum)

You are recording research observations for the AGET knowledge base.

Renamed: /aget-record-observation/aget-record-observation per S-V-O naming convention (L584) and ACM SIGSOFT "Observation" grounding.

Input

$ARGUMENTS

Mode Detection

Detect the input mode based on $ARGUMENTS:

Input Pattern Mode Behavior
Empty or blank Autonomous Scan session, identify and capture valuable signals (~2 min)
Time pattern: 5min, 10 min, 20min, 30 min Time-Budget Scan session with depth scaled to time budget
Text with signal keywords Explicit Capture the specific signal provided
Other text Explicit Capture as general observation

Mode 1: Autonomous (no args)

When invoked as /aget-record-observation with no arguments:

  1. Scan recent session conversation for valuable signals
  2. Identify vocabulary candidates, patterns, RQs, findings, gaps
  3. Prioritize by novelty and AGET governance value
  4. Capture top 3-5 signals to session file with classification
  5. Report what was captured

Mode 2: Time-Budget (duration arg)

When invoked as /aget-record-observation <duration> (e.g., /aget-record-observation 10min):

Time Budget Depth Actions
2-5 min Shallow Scan + capture raw signals to session file
10 min Medium Classify + link signals to existing vocabulary terms
20 min Deep Interlink + propose RQs + draft L-doc candidates
30+ min Full Formalize with traceability, update session summary

Mode 3: Explicit (signal arg)

When invoked as /aget-record-observation "<signal>":

Classify the input and route to appropriate target:

Signal Type Indicator Keywords Target Location
Vocabulary candidate "term:", "concept:", "definition:", "vocabulary" Session file - Vocabulary Candidates section
Research question "RQ:", "question:", "how does", "why does", "what is" Session file - Research Questions section
Web research finding "source:", "URL:", "according to", "web search" Session file - Web Findings section
L-doc draft "finding:", "lesson:", "L-doc", "learned:" Session file - Findings section
Pattern observation "pattern:", "anti-pattern:", "noticed:", "observed:" Session file - Patterns section
Process gap "gap:", "missing:", "SOP:", "template:" Session file - Process Gaps section
General observation (default) Session file - Observations section

Read the full file on GitHub · 116 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. 8d ago First seen · 116 lines · 42 tokens per session scan A ce2bbe98f535

Subscribe to this mod's changes

aget-record-observation is a skill published in the GitHub repository aget-framework/aget (11 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 1,213 once invoked, about $0.0002 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.