Borrowing it
Nothing to install: this file belongs to vladm3105/aidoc-flow-framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vladm3105/aidoc-flow-framework/dev/.agents/skills/self-learn/SKILL.mdgit clone --depth 1 https://github.com/vladm3105/aidoc-flow-frameworkWrote 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/vladm3105/aidoc-flow-framework/self-learn)<a href="https://agentmods.dev/skills/vladm3105/aidoc-flow-framework/self-learn"><img src="https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/self-learn/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/vladm3105/aidoc-flow-framework/self-learn"><img src="https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/self-learn.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 | $0.00051 | $0.02471 |
| Opus 5.5 | $0.00020 | $0.00988 |
| Sonnet 5.5 | $0.00010 | $0.00494 |
| Haiku 4.5 | $0.00005 | $0.00247 |
Grade A, and why
self-learn 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 29d 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-learn
A lesson learned twice and written nowhere will be learned a third time. This
skill is the shared loop over the repo-declared memory store (project memory,
session checkpoint, recall, memory-hygiene): where the active repository
declares its own learning spec or store, that declaration is authoritative for
categories, qualification, and file paths, and this skill defers to it. The
loop is engine-agnostic — it must work identically for any capable agent
(Claude Code, Codex, Copilot, custom harnesses). Harness-provided artifacts
(session checkpoints, notes files, trajectory stores) are optional inputs,
resolved at runtime: use them when the harness exposes them, fall back to
portable sources (git log, session notes, the repo tracker) when it does
not. Never hardcode another harness's paths, schemas, or store names.
The loop has three modes. Run only the mode the situation calls for.
| Mode | When | Cost |
|---|---|---|
apply |
session start, after task selection | cheap — read, don't write |
capture |
mid-work, when a correction or hard-won gotcha lands | cheap — one entry, one place |
consolidate |
after significant work, on schedule, when patterns recur | expensive — full cycle §4–§7 |
1. Resolve the stores
| Store | Location | Purpose |
|---|---|---|
| Learnings | .aidoc/learning/learnings.md (repo-owned system of record, by PR) |
this loop's home — harness memory is the scratch inbox, resolved per recall §1 |
| Session state | the harness's session checkpoint / notes (filenames resolved at runtime, never assumed) | extraction sources |
| Verbatim recovery | the harness's trajectory store, if it exposes one | exact payloads when memory paraphrases |
| Project learning log | only where the repository declares one (own path, own schema) | repo-owned audit trail |
Portable sources work everywhere: git log, the repo tracker, and the current
session's own notes. Harness-specific rows above are best-effort — when the
harness exposes no checkpoint, notes, or trajectory store, run the loop on the
portable sources alone rather than failing. Memory summaries keep intent but
drop literals; real evidence lives in the session's discovered-knowledge and
errors-and-fixes records, the trajectory store's tool-input rows (when one
exists), and git log.
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.
- 29d ago Changed f00018c2be35
- 1mo ago Changed · +22 lines 2844b0d9c12f
- 1mo ago First seen · 187 lines · 51 tokens per session scan A a07c7610e96d
self-learn is a skill published in the GitHub repository vladm3105/aidoc-flow-framework (17 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 2,471 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 2026-09-28.
Other skills, from other repositories
knowledge-ingest
Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, source notes, and cross-links; also learn durable lessons from a set of conversations, transcripts, or past sessions (/learn), including the Learn from conversations and Learn from Memory…
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
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…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…