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 SYZ-Coder/superpowers-openspec-team-skills --skill superpowers-learning-workflowgit clone --depth 1 https://github.com/SYZ-Coder/superpowers-openspec-team-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/syz-coder/superpowers-openspec-team-skills/superpowers-learning-workflow)<a href="https://agentmods.dev/skills/syz-coder/superpowers-openspec-team-skills/superpowers-learning-workflow"><img src="https://agentmods.dev/badge/skills/syz-coder/superpowers-openspec-team-skills/superpowers-learning-workflow/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/syz-coder/superpowers-openspec-team-skills/superpowers-learning-workflow"><img src="https://agentmods.dev/badge/skills/syz-coder/superpowers-openspec-team-skills/superpowers-learning-workflow.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 | $0.00036 | $0.01042 |
| Opus 5.5 | $0.00014 | $0.00417 |
| Sonnet 5.5 | $0.00007 | $0.00208 |
| Haiku 4.5 | $0.00004 | $0.00104 |
Grade A, and why
superpowers-learning-workflow 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 1mo 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Superpowers Learning Workflow
Overview
Use this workflow after meaningful work to capture what should survive the current session. It is a lightweight, repo-owned learning loop inspired by reflective agent systems, but scoped for safe use inside normal project workflows.
This is an explicit opt-in workflow. Do not use it by default. Only use it when the user explicitly asks for this workflow, names this skill, or a repository policy explicitly requires it.
Workflow
- Review the recent work, decisions, and verification evidence.
- Classify what was learned into four buckets:
- durable project facts
- current working state
- session outcome
- reusable method or repeated pitfall
- Add required metadata for durable entries:
idstatusconfidencesourcelast_updatedreview_afterDo not mark an entry asverifiedifsourceis empty.
- If
.superpowers-memory/exists, update:PROJECT_CONTEXT.mdfor durable factsCURRENT_STATE.mdfor active stateDECISIONS.mdfor lasting decisionsKNOWN_FAILURES.mdfor repeated failure patternsVERIFICATION_BASELINE.mdfor trusted verification rulesTEAM_PREFERENCES.mdfor durable team agreementsUSER_PROFILE.mdfor durable user preferences that are not project factsAGENT_NOTES.mdfor durable execution reminders that are not project factssession-journal/for the session summaryLEARNING_BACKLOG.mdfor reusable patterns that may deserve future workflows or skills
- If
.superpowers-memory/does not exist, tell the user to install the memory scaffold or keep the learning summary in a normal project doc. - Check whether any backlog item is strong enough to recommend promotion into a checklist, project rule, workflow step, script, or skill draft.
- Review
.superpowers-memory/SESSION_CLOSE_CHECKLIST.mdbefore finishing the learning capture. - Use
scripts/suggest-superpowers-memory-updates.ps1if it is unclear which memory surfaces should be updated from the current session signals. - Prefer
scripts/run-superpowers-memory-closeout.ps1as the standard closeout helper when you want one command to review the checklist, get update suggestions, and optionally run validation. - When memory files were updated, run
scripts/validate-superpowers-memory.ps1and include the result in the summary. - Use
scripts/search-superpowers-memory.ps1when you need to confirm whether a pattern already exists in durable memory or recent journals. - Summarize what was learned and what, if anything, should become a future rule, checklist, script, or skill.
What ships with it
4 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.
- 1mo ago First seen · 84 lines · 36 tokens per session scan A ecfe91d68088
superpowers-learning-workflow is a skill published in the GitHub repository SYZ-Coder/superpowers-openspec-team-skills (200 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 1,042 once invoked, about $0.0001 per session on Opus 5.5. 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
Migrate
Intakes external content (notes, CLAUDE.md, Cursor rules, Obsidian/Notion/Apple Notes exports), classifies chunks against the LifeOS taxonomy, and commits with provenance after confidence-tiered approval. USE WHEN /migrate, migrate content, import from other LifeOS, bring in old notes, import Cursor rules, import…
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
wiki-dashboard
Create dynamic, queryable Obsidian dashboard views using Bases or Dataview. Use for auto-updating tables, indexes, or structured views of vault content; not for ordinary question answering.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
session-compact
AI DevKit · Compact a historical AI coding session with Jev when context is long, work is handed off or resumed, or durable continuation facts and memory candidates need extraction.
daily-briefing
Proactive daily briefing that fires on a recurring schedule, pulls recent memory and workspace context, composes a structured summary (action items, progress, radar, next steps), and delivers it to all active channels. Enable with a time like "set up my daily briefing at 9am". Disable, reschedule, or check status at…