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 ralfyishere/rules-with-receipts --skill self-improvement-loopgit clone --depth 1 https://github.com/ralfyishere/rules-with-receiptsWrote 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/ralfyishere/rules-with-receipts/self-improvement-loop)<a href="https://agentmods.dev/skills/ralfyishere/rules-with-receipts/self-improvement-loop"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/self-improvement-loop.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 | $0.00111 | $0.01640 |
| Opus 5 | $0.00056 | $0.00820 |
| Sonnet 5 | $0.00022 | $0.00328 |
| Haiku 4.5 | $0.00011 | $0.00164 |
Grade A, and why
Self-Improvement Loop 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 8d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Improvement Loop
Purpose
A correction that only fixes the current output is a discount on future mistakes left unclaimed. This skill converts failures — user corrections, dead-end approaches, repeated friction — into short, reusable lessons, and ensures the next attempt actually incorporates them rather than re-running the failed pattern with fresh confidence.
When to use this skill
- The user corrects you: content, approach, tone, scope, format. Every correction encodes a rule they expected you to already know.
- An attempt failed and you're about to retry — the loop runs between attempts, not after the third identical failure.
- You notice a pattern: the same kind of flag ignored, the same misreading of intent, the same class of bug in your changes.
- At the end of significant work: a multi-step task, a hard debug, anything with lessons worth keeping.
When NOT to use this skill
- Mid-flow on trivial slips (a typo you immediately fixed). The loop is for patterns and real failures, not every micro-error.
- As public self-flagellation: the user needs the corrected work and maybe one line of what changed — not an essay of apology. The review is mostly internal; its output is behavior.
- When the "failure" was actually a requirements change — that's
memory-hygiene's superseded-context handling, not a lesson about your process.
Operating procedure
Step 1 — On any correction or failure, stop before retrying. The reflex to immediately re-attempt is how the same mistake happens twice with better vocabulary.
Step 2 — Run the lightweight after-action review (four lines; internal by default):
Goal: what was I trying to produce?
Actual: what happened / what did the user push back on?
Root: why - the earliest point where the path went wrong?
Lesson: one sentence, phrased as a rule for NEXT time.
The Root line matters most: "the fix was wrong" is a symptom; "I diagnosed from the error message without reproducing" is a root. Push to the earliest wrong turn — it's usually a skipped step from one of the sibling skills.
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.
- 8d ago First seen · 94 lines · 0 tokens per session scan A cf6e13eb19df
Self-Improvement Loop is a skill published in the GitHub repository ralfyishere/rules-with-receipts (2 stars, last pushed 1mo ago), licensed MIT. It adds 111 tokens to every session and 1,640 once invoked, about $0.0006 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.
Other skills, from other repositories
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
setup-matt-pocock-skills
A setup skill that configures engineering skills for a repository, including its issue tracker, labels, and documentation layout. A repository is the project folder managed by version control.
frontend-design
A design guide for building polished web interfaces such as pages, dashboards, forms, navigation, and reusable UI components. It covers HTML, CSS, JavaScript, and common frontend frameworks.
alterlab-cobrapy
Build and analyze genome-scale constraint-based metabolic models with COBRApy — flux balance analysis (FBA), flux variability analysis (FVA), gene and reaction knockouts, flux sampling, and SBML model I/O. Use when simulating metabolic networks, predicting growth or knockout phenotypes, or running systems-biology and…
alterlab-depmap
Query the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores (CRISPR Chronos), drug sensitivity data, and gene effect profiles. Use when identifying cancer-specific genetic vulnerabilities, finding synthetic lethal interactions, checking whether a gene is essential in given cell lines, or…
alterlab-qutip
Simulates open quantum systems with QuTiP, the Quantum Toolbox in Python, solving Lindblad master equations (mesolve), Monte Carlo trajectories (mcsolve), and unitary dynamics (sesolve). Use when studying master-equation or Lindblad dynamics, decoherence, dissipation, quantum optics, cavity QED, or open-system time…