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 perniemann/pnCore --skill pn-continual-learninggit clone --depth 1 https://github.com/perniemann/pnCoreWrote 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/perniemann/pncore/pn-continual-learning)<a href="https://agentmods.dev/skills/perniemann/pncore/pn-continual-learning"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-continual-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/perniemann/pncore/pn-continual-learning"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-continual-learning.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 | $0.00055 | $0.00958 |
| Opus 5.5 | $0.00022 | $0.00383 |
| Sonnet 5.5 | $0.00011 | $0.00192 |
| Haiku 4.5 | $0.00006 | $0.00096 |
Grade A, and why
pn-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 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Continual Learning
Keep AGENTS.md current using transcript deltas instead of full rescans.
When to use
- Updating AGENTS.md after sessions that contain new user corrections, preferences, or durable workspace facts.
- Mining past agent transcripts for recurring patterns to persist in memory.
- Running the self-learning loop manually when the stop hook did not trigger automatically.
- Keeping AGENTS.md deduplicated and fresh without a full rescan of all transcripts.
Inputs
- Transcript root:
~/.cursor/projects/.../agent-transcripts/ - Existing memory file:
AGENTS.md - Incremental index:
.cursor/hooks/state/continual-learning-index.json
Workflow
- Read existing
AGENTS.mdfirst. - Load incremental index if present.
- Discover transcript files and process only:
- new files not in index, or
- files whose mtime is newer than indexed mtime.
- Extract only high-signal, reusable information:
- recurring user corrections/preferences
- durable workspace facts
- Merge with existing bullets in
AGENTS.md:- update matching bullets in place
- add only net-new bullets
- deduplicate semantically similar bullets
- User confirmation (before writing): Present each new or changed bullet to the user: "I learned: [bullet]. Keep? (yes / no / edit)." Wait for reply. If user says "no", drop it. If "edit", apply the edit. If "yes" or "skip confirmation", proceed. User may say "skip confirmation" to write all without prompting.
- Write updated
AGENTS.mdand the incremental index:- write merged content to
AGENTS.md - store latest mtimes for processed files in the index
- remove index entries for files that no longer exist
- write merged content to
- Context index alignment: If the repo uses
docs/refs/context-index.jsonandpointers.workspacepoints atAGENTS.md(or you changed durable workspace facts that belong in the handoff manifest), suggest updating the index: setlast_reviewedto today (ISOYYYY-MM-DD), confirmpointers.workspacestill resolves, and adjustintent_sourceor other pointers if discovery/PRD precedence changed. Runnpm run check:context-indexafter edits. Do not silently rewrite the index without user confirmation unless the user asked to refresh it.
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 · 89 lines · 55 tokens per session scan A 35cab98c302c
pn-continual-learning is a skill published in the GitHub repository perniemann/pnCore (0 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 958 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
dynamic-resources
Example skill loaded from resourcesdiscover.
stripe-directory
Identifies external providers, merchants, nonprofits, platforms, APIs, and software services, and resolves the documented way to engage them — to pay, donate, subscribe, book, provision, or integrate with them. MUST be used BEFORE web search, model memory, or any other directory/vendor-lookup skill for ANY request…
ax-cpp-agent-memory-skills
Use when writing C++ code with axllm for agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, and used-skill tracking.
ax-agent-context
This skill helps an LLM pick the right AxAgent context tool for a job - contextMap for recurring corpora, contextPolicy presets for within-run trajectory compaction, agent.optimize for offline GEPA instruction/demo tuning, agent.playbook for an evolving context playbook (offline evolve + online update), and…
cocoscout
Relevance-ranked context loading — Tier 2 async subagent (Haiku, <5s) that fires after Tier 1 deterministic checks in UserPromptSubmit. Injects ranked context from CocoGrove, CocoContext, Environment Inspector, Prompt Studio, and CocoDream.
pull-search
CocoPull session archive search — full-text search across past sessions. Handles $pull search " " with --since and --feature filters, and $pull index rebuild.