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 skills add aget-framework/template-advisor-aget --skill aget-record-lessongit clone --depth 1 https://github.com/aget-framework/template-advisor-agetWrote 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/aget-framework/template-advisor-aget/aget-record-lesson)<a href="https://agentmods.dev/skills/aget-framework/template-advisor-aget/aget-record-lesson"><img src="https://agentmods.dev/badge/skills/aget-framework/template-advisor-aget/aget-record-lesson/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.
<a href="https://agentmods.dev/skills/aget-framework/template-advisor-aget/aget-record-lesson"><img src="https://agentmods.dev/badge/skills/aget-framework/template-advisor-aget/aget-record-lesson.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00039 | $0.01948 |
| Opus 5.5 | $0.00016 | $0.00779 |
| Sonnet 5.5 | $0.00008 | $0.00390 |
| Haiku 4.5 | $0.00004 | $0.00195 |
Grade A, and why
aget-record-lesson 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 15d 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.
This is a copy
100% identical to aget-record-lesson — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/aget-record-lesson
Record lessons learned as structured L-docs in the git repo. Each lesson is classified to determine storage location and ID scheme.
Purpose
Capture learnings in a persistent, searchable format that survives context windows and session boundaries. Enables knowledge accumulation across sessions.
Input
$ARGUMENTS - Optional lesson description or trigger context
Execution
Step 1: Gather Context
Identify what triggered the lesson:
- Session observation
- User feedback
- Error encountered
- Pattern discovered
- Process improvement
Step 2: Classify the Lesson
Classify each distinct lesson using the rubric below. An explicit principal classification takes precedence; do not ask the principal to confirm a classification already supplied. Seat identity is context, not evidence of who benefits. A local incident can establish a portable lesson; a lesson from a framework-manager can remain Domain.
Classification rubric
Judge the core lesson, not the example's vocabulary. For each dimension record a short evidence-based answer internally; use Unknown when evidence is insufficient. These are decision criteria, not points that can compensate for a contradictory answer.
| Dimension | Framework evidence | Domain evidence |
|---|---|---|
| Portability | Another AGET with a different principal and domain can apply the corrective rule unchanged | The useful rule depends on this principal, client, platform configuration, or subject matter |
| Local dependence | Removing identifying details leaves a specific, actionable agent/process lesson | Removing local facts removes the useful content; a generic slogan is not a portable lesson |
| Routing consequence | An L-doc would improve agent verification, coordination, governance, or reusable operation | A local knowledge pattern would help the principal operate or understand the domain |
Obvious Framework: an actionable portable rule survives removal of local details and its useful consequence is agent/process improvement, with no material contrary evidence. Record Framework directly. Obvious Domain: the useful content is the local/domain fact or procedure and no substantive portable agent lesson remains. Record Domain directly. Do not manufacture a Framework abstraction from every fact. Mixed: both a portable rule and independently useful local knowledge deserve preservation. Recommend Split with the proposed boundary; confirm the two outputs unless the principal already authorized them. Ambiguous: an Unknown or contradiction changes the storage/routing choice. Ask one focused question about that distinction, with a recommendation; do not present an unexplained taxonomy menu. For multiple lessons, record the obvious ones and bundle only the unresolved classifications into one question.
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.
- 15d ago Changed 524ed408a3dc
- 1mo ago Changed · +32 lines e47edb08d634
- 1mo ago First seen · 192 lines · 39 tokens per session scan A dee908c7f924
aget-record-lesson is a skill published in the GitHub repository aget-framework/template-advisor-aget (2 stars, last pushed 8d ago), licensed Apache-2.0. It adds 39 tokens to every session and 1,948 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to aget-record-lesson, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
metagit-context-pack
Token-efficient workspace onboarding via tiered context packs — map, repo cards, session digest, objectives, approvals, repomix profiles. Use at session start or when scoping work in a metagit-managed workspace.
gh
GitHub CLI skill for interacting with GitHub via the gh command line tool. Use when Bub needs to (1) Create, view, or manage GitHub repositories, (2) Work with issues and pull requests, (3) Create and manage releases, (4) Run and monitor GitHub Actions workflows, (5) Create and manage gists, (6) Install and manage…
pypi-release
This skill should be used when releasing tunacode-cli to PyPI. It keeps the existing local release checks, then hands the actual PyPI upload to a GitHub Actions workflow that uses the repository's PYPIAPITOKEN secret.
clawrium-release-announcements
Daily — draft a release blog post, open a PR, iterate on comments until merged.
blog-author
Watch ric03uec/clawrium release tags; draft a short blog post per user-visible feature as a PR against blog/.
release-watcher
Watch upstream Claw releases and clawrium discussions; surface top 3 feature candidates to Devashish via Discord DM for approve/skip.