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 0dayInc/pwn --skill curriculumgit clone --depth 1 https://github.com/0dayInc/pwnWrote 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/0dayinc/pwn/curriculum)<a href="https://agentmods.dev/skills/0dayinc/pwn/curriculum"><img src="https://agentmods.dev/badge/skills/0dayinc/pwn/curriculum.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 | $0.00023 | $0.00790 |
| Opus 5 | $0.00012 | $0.00395 |
| Sonnet 5 | $0.00005 | $0.00158 |
| Haiku 4.5 | $0.00002 | $0.00079 |
Grade A, and why
pwn-ai-agent-curriculum 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 7d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PWN::AI::Agent::Curriculum
PWN::AI::Agent::Curriculum is Tier 4/5 of the pwn-ai reinforcement loop — the SELF-PLAY layer that turns the agent from a passive experience-recorder into an active learner: S1 .practice — Mistake-driven auto-curriculum. Reads Mistakes.top(unresolved), asks Reflect to generate 3 minimal reproducer prompts per signature, self-plays each under Loop.run, and auto-mistakes_resolve when Reward.judge says the practice run solved it. THE AGENT PRACTISES ITS OWN WEAKNESSES OVERNIGHT. S2 .counterfactual — On a repeated in-turn failure, forks: branch A continues with the correction_hint, branch B asks an alt persona for a different tool. Reward.judge picks the winner; (loser, winner) → Reward.record_preference. Real advantage estimation, not imagined rollouts. S3 .critic — Constitutional critic persona with TOOL ACCESS (can shell/extro_verify the claim). Runs BEFORE note_outcome; its verdict feeds Reward.judge and its concrete flaw becomes a preference pair when the agent self-corrects. S4 .red_team_plan — After plan_first, an adversarial persona reviews the plan against THIS host's Metrics/Mistakes/extro_drift and injects a pre-emptive correction_hint on the step it predicts will fail. C3 .hindsight — Hindsight Experience Replay. On failure, asks the judge "what DID this trajectory accomplish?", relabels the episode with the achieved-goal as success:true. Free positive samples from failures — first HER on real tool traces. W2 .train_and_gate — export_finetune + export_dpo → local LoRA (unsloth/axolotl if installed) → replay Mistakes.top on vN vs vN+1 → promote iff resolved(N+1) > resolved(N). Fully autonomous weight-level self-improvement with a regression gate. W3 .calibrate — Tracks plan_first predicted p(success) vs actual outcome → Brier score in Metrics. All entry points are cron-safe (never raise into the caller) and depth-guarded via Swarm's Thread.current[:pwn_swarm_depth] so a curriculum run cannot recurse into itself.
When to use
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.
- 7d ago First seen · 59 lines · 23 tokens per session scan A 896e08d38ae7
pwn-ai-agent-curriculum is a skill published in the GitHub repository 0dayInc/pwn (78 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 790 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…
supabase
Supabase / PostgREST Row-Level-Security playbook — pull the anon (or leaked servicerole) key out of the frontend JS, map tables from the auto-generated OpenAPI spec, test anonymous RLS READ disclosures (PII/secret leaks), and anonymous RLS WRITE abuse (insert/update/delete — e.g. forging…
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.
graphql
GraphQL pentest playbook — find the endpoint, dump the schema (introspection or field-suggestion fallback), then test for authorization gaps, query batching, alias overload, depth-based DoS, and SQLi/NoSQLi in resolver arguments. Use when the target exposes a /graphql endpoint, GraphiQL, Apollo, or accepts GraphQL…
jwt
JWT attack playbook — algorithm confusion (alg=none, HS/RS confusion), kid path traversal/SQLi, jku/x5u SSRF, weak HS256 cracking, and embedded JWK trickery. Use when the target uses JWTs for auth (header.payload.signature).