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 agentmods add skills/0dayinc/pwn/learningnpx skills add 0dayInc/pwn --skill learninggit clone --depth 1 https://github.com/0dayInc/pwnWhat 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 | $0.00020 | $0.00563 |
| Opus 5 | $0.00010 | $0.00282 |
| Sonnet 5 | $0.00004 | $0.00113 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
pwn-ai-agent-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 2d 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.
What it actually says
PWN::AI::Agent::Learning
PWN::AI::Agent::Learning is the self-improvement engine that closes the pwn-ai feedback loop. It captures task outcomes, mines session transcripts for durable lessons, promotes successful workflows into reusable skills, and keeps ~/.pwn lean (memory + learning.jsonl + mistakes + sessions) so the agent gets sharper over time instead of accumulating noise. Data flows: Loop.run --(tool telemetry)--> Metrics.record Loop.run --(final answer)----> Learning.auto_introspect (opt-in) auto_introspect --(throttled)--> Learning.gc_stores! # ~/.pwn lean model --(tool calls)------> learning_note_outcome / _distill_skill PromptBuilder <----------------- Learning.to_context + Metrics.to_context Everything is file-backed under ~/.pwn so it survives across REPL restarts and is shared by every future session.
When to use
Call PWN::AI::Agent::Learning from pwn_eval when the task needs this module.
Do not reimplement it in shell.
Methodologies
Generated from pwn/ai/agent/learning.rb. Prefer the public class methods below.
Class methods take (opts = {}) and read opts.
How to call
PWN::AI::Agent::Learning.help
PWN::AI::Agent::Learning.note_outcome(opts)
Public methods
note_outcomeoutcomesstatsto_contextexemplars_forexport_finetunedistill_skillupdate_skillreflectauto_introspectflip_last_outcomeconsolidateresetreconcile_verdict_tagsprune_outcomesleangc_storespurge_noiseauthorshelpgc_stores!lean!prune_outcomes!reconcile_verdict_tags!
Source
pwn/ai/agent/learning.rb
Verification
PWN::AI::Agent::Learning.respond_to?(:note_outcome) after the
module is loaded. Read the source for parameter names.
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.
- 2d ago First seen · 69 lines · 20 tokens per session scan A 93c1403e5d76
pwn-ai-agent-learning is a skill published in the GitHub repository 0dayInc/pwn (76 stars, last pushed 4d ago), licensed MIT. It adds 20 tokens to every session and 563 once invoked, about $0.0001 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
analyzing-linux-elf-malware
Analyze malicious Linux ELF binaries — botnets, cryptominers, ransomware, and rootkits targeting Linux servers, containers, and cloud infrastructure — through static analysis, dynamic tracing, and reverse engineering of x8664 and ARM samples. Use when investigating Linux malware, triaging a suspicious ELF binary…
osmedeus-expert
Expert guide for the Osmedeus security automation workflow engine. Use when: (1) writing or editing YAML workflows (modules and flows), (2) running osmedeus CLI commands (scan, workflow management, installation, server), (3) configuring steps, runners, triggers, or template variables, (4) debugging workflow execution…
writing-great-skills
Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.
performing-jwt-none-algorithm-attack
Execute and test the JWT none algorithm attack to bypass signature verification by manipulating the alg header field in JSON Web Tokens.
performing-ai-assisted-vulnerability-discovery
Using LLMs to accelerate vulnerability research and pentest workflows — generating syntax-valid fuzzing seeds and evolving grammars, fine-tuned mutation dictionaries, parallel agent-based proof-of-vulnerability generation, and evidence-driven passive analysis of real HTTP traffic via the Burp MCP server. Covers…
ask-matt
Ask which skill or flow fits your situation. A router over the user-invoked skills in this repo.