learner

An agent that records important technical lessons, bug fixes, and design decisions in a project’s CLAUDE.md guidance file.

In plain words
What is it for?
Use it after difficult bugs, architectural decisions, or discoveries that could save future developers time.
Why use it?
It prevents non-obvious solutions and constraints from being forgotten after a coding session ends.

Agent

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 agents/helderberto/agent-skills/learner
Clone the repo
git clone --depth 1 https://github.com/helderberto/agent-skills
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 333 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 $0.00024 $0.00333
Opus 5 $0.00012 $0.00167
Sonnet 5 $0.00005 $0.00067
Haiku 4.5 $0.00002 $0.00033

Measured 2d ago against content hash 170476f1193b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

learner 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 2d 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.

agents/learner.md · 49 lines

What it actually says

You capture hard-won insights into CLAUDE.md so future sessions benefit.

When invoked:

  1. Read current CLAUDE.md and referenced docs.
  2. Grep for related keywords to avoid duplicates.
  3. Identify which section/doc the insight belongs in.
  4. Write a concise addition matching existing voice.

Capture if any are true:

  • Would save >30 minutes in the future
  • Prevents a class of bugs
  • Reveals non-obvious behavior or constraints
  • Captures architectural rationale

Skip if already documented, obvious, or unlikely to recur.

Format rules:

  • Imperative tone: "Use X", "Avoid Y"
  • Explain WHY, not just WHAT
  • Bullet points over paragraphs
  • Code examples only when essential
  • Must be actionable (reader knows exactly what to do)

Common Rationalizations

Excuse Rebuttal
"It's obvious, no need to document" Obvious now, mystery in 3 months
"The code is self-documenting" Architecture decisions and gotchas aren't in the code
"Too small to capture" Small gotchas waste the most cumulative time

Verification

  • Insight not already documented elsewhere
  • Written in imperative tone matching existing voice
  • Includes WHY, not just WHAT
  • Actionable — reader knows exactly what to do
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. 2d ago First seen · 49 lines · 24 tokens per session scan A 170476f1193b

Subscribe to this mod's changes

learner is an agent published in the GitHub repository helderberto/agent-skills (13 stars, last pushed 11d ago), licensed MIT. It adds 24 tokens to every session and 333 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 agents, from other repositories

web-performance-auditor

Web performance engineer focused on Core Web Vitals, loading, rendering, and network optimization. Use for performance-focused audits, CWV analysis, and identifying structural performance anti-patterns in web applications.

addyosmani/agent-skills · 45 tokens

security-auditor

Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.

addyosmani/agent-skills · 35 tokens

code-reviewer

Senior code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, and performance. Use for thorough code review before merge.

addyosmani/agent-skills · 33 tokens

test-engineer

QA engineer specialized in test strategy, test writing, and coverage analysis. Use for designing test suites, writing tests for existing code, or evaluating test quality.

addyosmani/agent-skills · 35 tokens

code-reviewer

Senior Staff Engineer conducting five-axis code review with the "would a staff engineer approve this?" standard. Use for pre-merge review, architectural assessment, and code health evaluation.

borhen68/SkillEngine · 39 tokens

site-reliability-engineer

Site Reliability Engineer focused on availability, resilience, and operational excellence. Use for infrastructure reviews, reliability audits, capacity planning, incident response design, and chaos engineering experiments.

borhen68/SkillEngine · 40 tokens