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 hardiktiwari/PM-operating-OS --skill continual-learninggit clone --depth 1 https://github.com/hardiktiwari/PM-operating-OSWrote 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/hardiktiwari/pm-operating-os/continual-learning)<a href="https://agentmods.dev/skills/hardiktiwari/pm-operating-os/continual-learning"><img src="https://agentmods.dev/badge/skills/hardiktiwari/pm-operating-os/continual-learning.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 | $0.00051 | $0.01213 |
| Opus 5 | $0.00026 | $0.00607 |
| Sonnet 5 | $0.00010 | $0.00243 |
| Haiku 4.5 | $0.00005 | $0.00121 |
Grade A, and why
continual-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 8d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Continual Learning
The ingestion pipeline for the PM-OS context graph. Reads chat transcripts, classifies what it finds, writes structured entries to memory/, and updates AGENTS.md with curated preferences and facts.
When to Use
- "Run continual learning" / "mine my chats" / "update memory"
- On a schedule (e.g. end of week) to keep the context graph current
- After a batch of important conversations (strategy sessions, PRD reviews, planning)
Inputs
- Transcript root:
~/.cursor/projects/<workspace-slug>/agent-transcripts/ - Existing memory:
AGENTS.md+memory/subdirectories - Incremental index:
.cursor/hooks/state/continual-learning-index.json
Workflow
1. Load state
- Read existing
AGENTS.md. - Load incremental index (if present).
- Discover transcript files. Process only:
- new files not in the index, or
- files whose mtime is newer than the indexed mtime.
2. Extract and classify
For each new/changed transcript, extract high-signal items and classify each into one of these categories:
| Category | What to look for | Write to |
|---|---|---|
| Decision | User made or confirmed a product decision (PRD approval, scope change, launch/kill, prioritization shift, stakeholder alignment) | memory/decisions/ |
| Exec update | User drafted or discussed an executive status update, SLT summary, or program update | memory/exec-updates/ |
| Strategy shift | User discussed or changed strategic direction, pillars, positioning, or goals | memory/strategy-reviews/ |
| Feedback insight | User analyzed customer feedback, VOC themes, or support trends | memory/feedback/ |
| User preference | Recurring correction or stated broad rule about how the AI should behave | AGENTS.md → Learned User Preferences |
| Workspace fact | Durable fact about the workspace, tools, file paths, or workflows | AGENTS.md → Learned Workspace Facts |
Skip: one-off task instructions, transient details (branch names, commit hashes, temp errors), secrets/tokens/credentials, and anything not actionable in future sessions.
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.
- 8d ago First seen · 169 lines · 51 tokens per session scan A 450d73132220
continual-learning is a skill published in the GitHub repository hardiktiwari/PM-operating-OS (5 stars, last pushed 4mo ago), licensed MIT. It adds 51 tokens to every session and 1,213 once invoked, about $0.0003 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
kayba-ace
This skill ships learnfromtraces.py, a script that reads OpenClaw session transcripts, feeds them through the ACE learning pipeline, and writes an updated skillbook to disk.
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
lean-ctx
Local context tooling for AI agents. Use it to select, shape, reuse, recover, and inspect context before inference when reading files, running shell commands, searching code, or exploring directories.
lean-ctx
Local context tooling for AI agents. Use it to select, shape, reuse, recover, and inspect context before inference when reading files, running shell commands, searching code, or exploring directories.
cep-wizard
Launch a local, localhost-only browser wizard with two journeys — layout onboarding for a project with ult-repo-layout installed, initialized or not — guides an uninitialized or not-yet-discovered repo through Run Discover, then shows resolved layer/slot state through four labeled boxes and a directory picker, and…
institutional-memory-distill
Distill decisions, reasoning, and rejected alternatives from PRs, design docs, and postmortems into the project's decisionledger, so ult-context-generate's trip-wire can surface institutional memory before new work quietly repeats settled ground. Do NOT use to query the ledger against new work or decide…