simplicio-learn

A learning and retrospective workflow that extracts a small set of useful lessons from completed agent runs and saves them in project instructions or memory.

In plain words
What is it for?
Use it after a run, during session wrap-up, or when asked to remember a correction, review what happened, or update project memory.
Why use it?
It prevents the agent from repeating known mistakes and preserves successful command patterns and other high-value corrections for later work.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/wesleysimplicio/simplicio-loop/simplicio-learn
Any agent
npx skills add wesleysimplicio/simplicio-loop --skill simplicio-learn
Clone the repo
git clone --depth 1 https://github.com/wesleysimplicio/simplicio-loop

Made for: Claude Code, Codex.

Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,302 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00109 $0.01302
Opus 5 $0.00055 $0.00651
Sonnet 5 $0.00022 $0.00260
Haiku 4.5 $0.00011 $0.00130

Measured 2d ago against content hash b79a0d8fb5a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

simplicio-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 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.

.claude/skills/simplicio-learn/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

simplicio-learn — retrospective & continual memory

A run that doesn't record its lessons pays full price every time. This skill turns a finished run (or session) into a few durable, reusable bullets and writes them where the NEXT run will read them — closing the simplicio-tasks trajectory/learn/reuse_precedent loop.

Credit: folds cursor continual-learning (transcript-driven, incremental, high-signal-only memory updates with an index to avoid reprocessing) and teaching (a retrospective step that updates persistent state so the next cycle doesn't re-derive what's known).

When to use

  • After simplicio-tasks finishes its Step 6 self-audit (per-item and per-run).
  • At session end (bind to a stop hook where available — see hooks/).
  • "remember this", "retrospective", "what did we learn", "update the project memory".

What to capture (high-signal only)

Three durable categories — everything else is noise and is dropped:

  1. Corrections — a command that failed then a near-identical one succeeded. Record {wrong-pattern → right-pattern, error-class, count}. Classify the error (unknown-flag, command-not-found, wrong-syntax, wrong-path, missing-arg, permission-denied). Keep only pairs above ~0.6 command-similarity. EXCLUDE compile/test failures (those are the Step 4 iterate-until-green loop, not a CLI lesson) and human-rejections (a declined action is not an error).
  2. Solved precedents — a problem fingerprint → the solution shape that worked, so a future matching item is REUSED not regenerated. Store fingerprint + PR/commit link + the key edit.
  3. Bug patterns — structured root-cause pattern store (.simplicio/orchestrator/patterns.jsonl). Each entry:
    • fingerprint: sha256 of root_cause + file
    • root_cause: the mechanism-level root cause
    • symptom_pattern: observable behavior
    • fix_summary: what fixed it
    • sibling_files: related files changed
    • hit_count: incremented when the same fingerprint is seen again
    • last_seen: ISO timestamp

Read the full file on GitHub · 99 lines

Changes

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.

  1. 2d ago First seen · 99 lines · 109 tokens per session scan A b79a0d8fb5a7

Subscribe to this mod's changes

simplicio-learn is a skill published in the GitHub repository wesleysimplicio/simplicio-loop (2 stars, last pushed 2d ago), licensed MIT. It adds 109 tokens to every session and 1,302 once invoked, about $0.0005 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.

Related

Other skills, from other repositories