insights

insights is a skill for Claude Code from aldianriski/lean-flow. It costs 110 tokens per session (1,012 once invoked), scanned A, original, MIT.

A quick learning log for recording a useful friction, surprise, confirmed assumption, or retrieval failure in docs/LEARNINGS.md. It can add a new learning or increase the count of a matching existing one.

In plain words
What is it for?
Use it mid-task or during quick work to capture a transferable lesson, record a repeated problem, or note that earlier project knowledge could not be found.
Why use it?
Lessons noticed during work can disappear before the end-of-sprint review. Recording them immediately preserves the cause and fix, helping repeated lessons become lasting project rules.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the lean-flow plugin — 15 skills shipped together

Good fit Use it mid-task or during quick work to capture a transferable lesson, record a repeated problem, or note that earlier project knowledge could not be found.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aldianriski/lean-flow/insights
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.

Any agent
npx skills add aldianriski/lean-flow --skill insights
Clone the repo
git clone --depth 1 https://github.com/aldianriski/lean-flow

Made for: Claude Code.

Or install lean-flow, the plugin that ships this one along with the rest of its 15 skills.

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 insights

README.md
[![agentmods](https://agentmods.dev/badge/skills/aldianriski/lean-flow/insights.svg)](https://agentmods.dev/skills/aldianriski/lean-flow/insights)
Your own site
<a href="https://agentmods.dev/skills/aldianriski/lean-flow/insights"><img src="https://agentmods.dev/badge/skills/aldianriski/lean-flow/insights.svg" alt="Measured on agentmods" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,012 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.
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 $0.00110 $0.01012
Opus 5 $0.00055 $0.00506
Sonnet 5 $0.00022 $0.00202
Haiku 4.5 $0.00011 $0.00101

Measured 7d ago against content hash 0f3cf3d2beb3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

insights 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 7d 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.

skills/insights/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

insights

Anytime learning capture. The Sprint-Close Retro batches learnings at a sprint boundary — but a friction noticed mid-work (or in quick-mode work that never closes a sprint) dilutes or vanishes by then. /insights captures it the moment it's felt, into the same docs/LEARNINGS.md ledger the Retro feeds, so the §10 promotion machinery (count ≥ 2 → durable rule) still sees it.

When to invoke

  • A friction, surprise, or "I'll remember this" moment lands mid-task — capture it before it fades.
  • Standalone / quick-mode work surfaced a lesson but won't reach a Sprint-Close Retro.
  • You spot a recurrence of something already in the ledger — bump it toward promotion.
  • A retrieval miss — you couldn't find, or you contradicted, a prior L-NNN/ADR — file it; it's the observed signal that knowledge retrieval is degrading.

Not for: durable project state (→ a commit / sprint record) · ending a session (→ /handoff) · the full sprint retro (→ /lean-doc-generator close).

Procedure

  1. Phrase the learning — one line: what was got wrong or confirmed and the fix. Vague venting isn't a learning; if there's no transferable fix, don't file it.

  2. Scan for a match — read docs/LEARNINGS.md; look for an existing entry on the same concept (not just a keyword hit). Note the next free L-NNN (max + 1) in case it's new.

  3. Recurrence → bump, don't duplicate — a concept-match means it recurred: add the current sprint or date to its seen, increment count, and surface it: "L-NNN now count N — promotable at the next promote (≥ 2)." Bumping is the promotion signal; it beats a second near-duplicate entry.

  4. New → draft the entry — self-contained shape (if the host repo bundles lean-doc-generator, its templates/LEARNINGS.md.template wins on divergence):

    ## L-NNN — <one-line: what was got wrong or confirmed, and the fix>
    - seen: <sprint or date>
    - count: 1
    - promoted: no   <!-- once count >= 2: yes -> <where it was promoted> -->
    - tags: <tag>   [status: active]
    

Read the full file on GitHub · 69 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. 7d ago First seen · 69 lines · 110 tokens per session scan A 0f3cf3d2beb3

Subscribe to this mod's changes

insights is a skill published in the GitHub repository aldianriski/lean-flow (5 stars, last pushed 8d ago), licensed MIT. It adds 110 tokens to every session and 1,012 once invoked, about $0.0006 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 2026-08-31.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens