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 abstractonion/cadence --skill capture-learningsgit clone --depth 1 https://github.com/abstractonion/cadenceWrote 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/abstractonion/cadence/capture-learnings)<a href="https://agentmods.dev/skills/abstractonion/cadence/capture-learnings"><img src="https://agentmods.dev/badge/skills/abstractonion/cadence/capture-learnings/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/abstractonion/cadence/capture-learnings"><img src="https://agentmods.dev/badge/skills/abstractonion/cadence/capture-learnings.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00035 | $0.00589 |
| Opus 5 | $0.00017 | $0.00295 |
| Sonnet 5 | $0.00007 | $0.00118 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
capture-learnings 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reflect: Capture One Durable Lesson
After a change ships, a bug is fixed, or a debugging session ends — name one thing the next session would benefit from knowing. This is the difference between a session that compounds and one that resets.
When to reflect
- After fixing a non-trivial bug (especially if it took more than one hypothesis).
- After shipping a feature whose design surprised you mid-implementation.
- After a review surfaced a class of issue you hadn't been watching for.
- When you noticed an undocumented constraint, a project-specific gotcha, or a recurring footgun.
What a useful learning looks like
A learning has four parts, even if it fits on one line:
- Pattern or pitfall — what to do, or what to avoid.
- Where it applies — which file/module/area, or which class of change.
- Why — the underlying reason, not just the symptom.
- Confidence — observed in this session (high) vs. inferred (lower). Be honest.
Example: "When adding a new status to the OrderState enum, also update notifyOnTransition() in notifications/order.ts — the dispatch table is keyed by enum and silently no-ops on unknown values. Observed: missed in the original change, caught in QA."
Learnings log paths
Append one dated entry per /reflect. Use the first path that exists; if neither exists, propose a path and ask the user once before writing:
docs/learnings.md.cadence/learnings.md
Bootstrap from Cadence's templates/learnings.md when starting a project log.
Solution docs
After a 3-strike investigation, a multi-hypothesis bug, or any fix you'd likely debug again — add docs/solutions/<slug>.md using the project's copy of templates/solutions/_template.md (Symptom, Root cause, Fix, Verification, Tags). One doc per distinct failure mode.
Where else it lands
Choose the lightest durable home when a full log line is not enough:
- A line in
TODOS.mdif it's a follow-up task. promote-recurring-learningsif promotion gates are met (≥3 same pitfall, ≥2 areas, or worth enforcement).- A short comment next to the surprising code, if the lesson is local.
- The PR description itself, if the lesson is about this PR's context only.
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 · 51 lines · 35 tokens per session scan A 199d74de160c
capture-learnings is a skill published in the GitHub repository abstractonion/cadence (4 stars, last pushed 3mo ago), licensed MIT. It adds 35 tokens to every session and 589 once invoked, about $0.0002 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.