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 strikersam/autonomous-ai-agency --skill self-improvegit clone --depth 1 https://github.com/strikersam/autonomous-ai-agencyWrote 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/strikersam/autonomous-ai-agency/self-improve)<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/self-improve"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/self-improve/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/strikersam/autonomous-ai-agency/self-improve"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/self-improve.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 | $0.00000 | $0.00407 |
| Opus 5 | $0.00000 | $0.00204 |
| Sonnet 5 | $0.00000 | $0.00081 |
| Haiku 4.5 | $0.00000 | $0.00041 |
Grade A, and why
self-improve 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 11d 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.
What it actually says
Skill: Self-Improve
Purpose
Enables the agent to analyze its own skill library, identify gaps or weaknesses, and propose or implement improvements to existing skills or new skill definitions.
When to Use
- After completing a complex task where no existing skill quite fit
- When patterns emerge across multiple issues/tasks that aren't yet captured as skills
- When a skill's instructions led to suboptimal results
- Periodically as a meta-maintenance task
Process
1. Audit Existing Skills
- Read all
.agents/skills/*/SKILL.mdfiles - Note skills that are vague, outdated, or missing key steps
- Identify overlapping skills that could be merged
2. Identify Gaps
- Review recent issue resolutions and pull requests
- List patterns that recurred but lacked a matching skill
- Consider what skills would have saved time or improved quality
3. Propose Improvements
- For each gap or weakness, draft a new or updated SKILL.md
- Follow the existing skill format (Purpose, When to Use, Process, Output, Notes)
- Keep skills atomic and composable — one concern per skill
4. Implement
- Write new skill files to
.agents/skills/<skill-name>/SKILL.md - Update existing skills in place if improving them
- Do not delete skills without a clear reason documented in the changelog
5. Validate
- Confirm new skills follow repository conventions
- Cross-reference new skills with existing ones to avoid duplication
- Add changelog entry under
[Unreleased]
Output
- One or more new or updated
.agents/skills/*/SKILL.mdfiles - A changelog entry summarizing what was added or changed
Notes
- Skills should be written for an AI agent audience, not human developers
- Prefer explicit step-by-step instructions over abstract descriptions
- When improving a skill, preserve its original intent unless the intent itself was wrong
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.
- 11d ago First seen · 47 lines · 0 tokens per session scan A 52888a73a546
self-improve is a skill published in the GitHub repository strikersam/autonomous-ai-agency (8 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 407 tokens. 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
assimilate-popular-workflows
This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable…
process-builder
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.
mcp-app-verification
Comprehensive verification checklists for MCP Apps. Tests with basic-host reference, validates handler-before-connect, text fallback, resource URI linking, single-file bundling, host styling, CSP, and legacy pattern detection.
mcp-app-scaffolding
Scaffolds MCP App project structure with correct directory layout, dependencies, entry points, and framework-specific templates. Handles React (useApp hook), Vanilla JS, Vue, Svelte, Preact, and Solid.
mcp-csp-investigation
Comprehensive Content Security Policy audit for MCP Apps in sandboxed iframes. Discovers all network origins, traces them to source, and generates CSP configuration for registerAppResource.
frontmatter-parsing
YAML frontmatter parsing and manipulation for .planning/ documents. Provides read, write, update, query, and validation operations on frontmatter blocks in GSD markdown artifacts.