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 arozumenko/sdlc-skills --skill capture-learninggit clone --depth 1 https://github.com/arozumenko/sdlc-skillsWrote 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/arozumenko/sdlc-skills/capture-learning)<a href="https://agentmods.dev/skills/arozumenko/sdlc-skills/capture-learning"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/capture-learning/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/arozumenko/sdlc-skills/capture-learning"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/capture-learning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00166 | $0.02793 |
| Opus 5 | $0.00083 | $0.01396 |
| Sonnet 5 | $0.00033 | $0.00559 |
| Haiku 4.5 | $0.00017 | $0.00279 |
Grade A, and why
capture-learning 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 9d 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capture Learning
The point is compounding: every non-trivial product discovery should make the next
similar one easier. A searchable store of problem -> outcome -> lesson triples in
docs/discovery/evidence/learnings/ is the simplest way to make that real — but only if
it is reconciled, not accreted. The learning store is written ONLY through the
reconcile protocol below, never blind-append.
This skill captures positive knowledge — what was learned, including from losses. A product anti-pattern lives here too, framed as a learning ("we tried X assuming Y, learned Y was false, so future similar work should test Y first"). A durable rule the product will follow belongs in a decision record instead (see "Learning vs decision record").
This runs at a natural pause or on explicit invocation — never interleaved with an in-flight pipeline step.
When to capture
| Capture? | Example (domain-neutral) |
|---|---|
| Yes | A hypothesis shipped and its outcome metric moved — record what moved it. |
| Yes | A hypothesis was tested (interviews, a prototype, a trial) and killed — record why the assumption broke. |
| Yes | A vendor / data source / external service behaved differently than its docs implied. |
| Yes | A product decision was made non-obviously, for a real reason that would not reconstruct from the decision record alone. |
| Skip | "We renamed a field" — not a learning. |
| Skip | Anything already covered in a decision record or the hypothesis itself. |
| Skip | "We'd do it differently next time" with no specific reason — a retro complaint, not a learning. |
Procedure
The full rules live in references/reconcile-protocol.md;
this is the operational summary. Do every step — the reconcile and the self-verification
are what separate a compounding store from a junk drawer.
1. Pick the track and mint the ID
- Knowledge track (the default) — a transferable rule learned from a discovery.
Template:
assets/learning-knowledge.md. - Problem track — a concrete problem that was hit and resolved.
Template:
assets/learning-problem.md.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 198 lines · 166 tokens per session scan A 9b28341d33a6
capture-learning is a skill published in the GitHub repository arozumenko/sdlc-skills (20 stars, last pushed 4d ago), licensed MIT. It adds 166 tokens to every session and 2,793 once invoked, about $0.0008 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.
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.