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/docxology/template/self-improvement-loopsnpx skills add docxology/template --skill self-improvement-loopsgit clone --depth 1 https://github.com/docxology/templateWrote 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/docxology/template/self-improvement-loops)<a href="https://agentmods.dev/skills/docxology/template/self-improvement-loops"><img src="https://agentmods.dev/badge/skills/docxology/template/self-improvement-loops.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 | $0.00145 | $0.04407 |
| Opus 5 | $0.00072 | $0.02204 |
| Sonnet 5 | $0.00029 | $0.00881 |
| Haiku 4.5 | $0.00015 | $0.00441 |
Grade A, and why
self-improvement-loops 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 6d 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.
This is a copy
100% identical to self-improvement-loops — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Improvement Loops
This skill covers systems where the harness is the artifact being optimized: an agent mines its own failures and edits its own scaffold, a meta-agent searches over harness code, a population of workflow candidates evolves against an evaluator, or the mechanism that produces context is itself versioned and improved. The design question shifts from "how do I control one loop" (harness-engineering) to "how do I let a loop rewrite parts of itself without corrupting the signal that steers it".
The controlling constraint across every published system: the loop optimizes whatever signal it is given, including the signal's own weaknesses. Design the loop assuming the optimizer will find every gap between the metric and the intent.
When to Activate
Activate this skill when:
- Building a loop where an agent proposes edits to its own harness, prompts, context playbook, or workflow based on mined failure patterns
- Designing meta-level search over harness or scaffold code: meta-agent search, tree search over workflow graphs, evolutionary program search with an LLM mutation operator
- Choosing acceptance criteria for any self-modifying agent system
- Evolving the mechanism that manages context (a skill, playbook, or context function) rather than hand-editing the context artifact
- Diagnosing a degenerating self-improvement loop: reward hacking, diversity collapse, context collapse, or silent stagnation
- Deciding which level of the optimization ladder (prompt, context, workflow, harness code, optimizer code) a recurring failure should be fixed at
Do not activate this skill for adjacent work owned by other skills:
- Governance of a single autonomous loop that does not modify itself: locked and editable surfaces, durable logs, rollback, novelty gates, PR preparation, and human approval boundaries belong to
harness-engineering. That skill defines the control surfaces; this skill defines what happens when the surfaces themselves become the optimization target. - Building the evaluator, regression suite, or quality gates that score candidates:
evaluation. - LLM-as-judge design, pairwise comparison, and bias mitigation for candidate scoring:
advanced-evaluation. - One-shot token efficiency, masking, or caching without an improvement loop:
context-optimization. - Remote sandboxes and background execution infrastructure for running the loop:
hosted-agents. - Whether to build the loop at all, pipeline shape, and cost estimation:
project-development.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 255 lines · 145 tokens per session scan A 699926720701
self-improvement-loops is a skill published in the GitHub repository docxology/template (19 stars, last pushed today), licensed Apache-2.0. It adds 145 tokens to every session and 4,407 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to self-improvement-loops, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
planning-with-files
Persistent file-based planning for multi-step AI-agent work. Keeps taskplan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and…
aerospace-engineering-technician
Use when a task needs the judgment of an Aerospace Engineering and Operations Technologist/Technician — verifying an installed fastener's preload against a drawing's torque callout via the T=K·D·F relationship, reducing strain-gauge data from a structural proof-load test into stress and checking it against an…
aviation-inspector
Use when a task needs the judgment of an Aviation Inspector — determining whether an air carrier's fleet is in compliance with an Airworthiness Directive across a maintenance-records sample, deciding where the FAA's compliance-and-enforcement ladder places a finding (compliance action vs. Letter of Correction vs.…
actor
Use when a task needs the judgment of a professional Actor — breaking down sides for a self-tape audition, preparing a character choice for rehearsal, deciding between two conflicting bookings, reading a contract offer for scale vs. scale-plus terms, or diagnosing why callbacks aren't converting to bookings.
agricultural-equipment-operator
Use when a task needs the judgment of an Agricultural Equipment Operator — calibrating planter seed population and singulation, diagnosing combine header or separator loss, sequencing planting or harvest across fields under a weather-constrained window, sizing machinery capacity in acres/hour against a season's…
agricultural-sciences-professor
Use when a task needs the judgment of a tenure-track or tenured Agricultural Sciences faculty member at a land-grant university — deciding whether to submit a grant this cycle versus wait, allocating time across the teaching/research/extension appointment split, diagnosing a stalled graduate student or field trial, or…