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 aldianriski/lean-flow --skill insightsgit clone --depth 1 https://github.com/aldianriski/lean-flowWrote 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/aldianriski/lean-flow/insights)<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>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 | $0.00110 | $0.01012 |
| Opus 5 | $0.00055 | $0.00506 |
| Sonnet 5 | $0.00022 | $0.00202 |
| Haiku 4.5 | $0.00011 | $0.00101 |
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.
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
-
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.
-
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 freeL-NNN(max + 1) in case it's new. -
Recurrence → bump, don't duplicate — a concept-match means it recurred: add the current sprint or date to its
seen, incrementcount, 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. -
New → draft the entry — self-contained shape (if the host repo bundles
lean-doc-generator, itstemplates/LEARNINGS.md.templatewins 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]
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.
- 7d ago First seen · 69 lines · 110 tokens per session scan A 0f3cf3d2beb3
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.
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.
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.…
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…
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.
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…
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.