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.
curl -O https://raw.githubusercontent.com/aget-framework/aget/main/.claude/skills/aget-record-lesson/SKILL.mdgit clone --depth 1 https://github.com/aget-framework/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/aget/aget-record-lesson)<a href="https://agentmods.dev/skills/aget-framework/aget/aget-record-lesson"><img src="https://agentmods.dev/badge/skills/aget-framework/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/aget/aget-record-lesson"><img src="https://agentmods.dev/badge/skills/aget-framework/aget/aget-record-lesson.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 148 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- aget-record-lesson — 100% identical, 0 lines differ
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/aget (12 stars, last pushed 7d 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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
aget-record-lesson
Record lessons learned from sessions as persistent, searchable, committable artifacts. Classifies each lesson as Framework (help other AGETs) or Domain (help principal).
aget-open-session
Open a session with context-aware establishment. Orchestrates wake-up, recovers prior session context, surfaces pending work, and proposes a session agenda.
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-release-critique
Adversarial review with the Critic perspective of the Release Delivery Triad (L818). Dual mandate — spec coverage audit plus deep bug finding, asking what breaks in the field and which assumptions are wrong. Superseded by /aget-check-release.
aget-release-audit-specs
Audit specifications with the Spec Auditor perspective of the Release Delivery Triad (L818) — coverage and consistency mode, asking whether a spec covers all behaviors and where gaps or contradictions remain. Superseded by /aget-check-release.
aget-release-build
Execute release gate deliverables with the Builder perspective of the Release Delivery Triad (L818) — speed-optimized execution asking whether the work is done, fast, and functional. Superseded by /aget-create-release.