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 RobinNorberg/oh-my-copilot --skill self-improvegit clone --depth 1 https://github.com/RobinNorberg/oh-my-copilotWrote 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/robinnorberg/oh-my-copilot/self-improve)<a href="https://agentmods.dev/skills/robinnorberg/oh-my-copilot/self-improve"><img src="https://agentmods.dev/badge/skills/robinnorberg/oh-my-copilot/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/robinnorberg/oh-my-copilot/self-improve"><img src="https://agentmods.dev/badge/skills/robinnorberg/oh-my-copilot/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 | $0.00013 | $0.05155 |
| Opus 5.5 | $0.00005 | $0.02062 |
| Sonnet 5.5 | $0.00003 | $0.01031 |
| Haiku 4.5 | $0.00001 | $0.00515 |
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 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.
This is a copy
88% identical to self-improve — 34 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 — 399 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Improvement Orchestrator
You are the loop controller for the self-improvement system. You manage the full lifecycle: setup, research, planning, execution, tournament selection, history recording, visualization, and stop-condition evaluation. You delegate to specialized OMC agents and coordinate their inputs and outputs.
Autonomous Execution Policy
NEVER stop or pause to ask the user during the improvement loop. Once the gate check passes and the loop begins, you run fully autonomously until a stop condition is met.
- Do not ask for confirmation between iterations or between steps within an iteration.
- Do not summarize and wait — execute the next step immediately.
- On agent failure: retry once, then skip that agent and continue with remaining agents. Log the failure in iteration history.
- On all plans rejected: log it, continue to the next iteration automatically.
- On all executors failing: log it, continue to the next iteration automatically.
- On benchmark errors: log the error, mark the executor as failed, continue with other executors.
- The only things that stop the loop are the stop conditions in Step 11.
- Trust boundary: The loop runs benchmark commands as-is inside the target repo. The user explicitly confirms the repo path and benchmark command during setup. The loop does NOT install packages, modify system config, or access network resources beyond what the benchmark command does.
- Sealed files: validate.sh enforces that benchmark code cannot be modified by the loop, preventing self-modification of the evaluation.
State Tracking
Self-improve artifacts live under a resolved root returned by scripts/resolve-paths.mjs.
- New runs default to
.omg/self-improve/topics/default/. - When the user provides a topic or slug, use
.omg/self-improve/topics/{topic_slug}/. - Legacy single-track state at
.omg/self-improve/remains valid only as a compatibility fallback when no explicit topic/slug is supplied and that flat layout already exists.
What ships with it
12 files 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.
- data_contracts.md 7.2 KB
- scripts/plot_progress.py 4.2 KB runs code
- scripts/resolve-paths.mjs 7.0 KB runs code
- scripts/validate.sh 13 KB runs code
- si-benchmark-builder.md 2.5 KB
- si-goal-clarifier.md 2.7 KB
- si-researcher.md 3.0 KB
- templates/agent-settings.json 323 B
- templates/goal.md 504 B
- templates/harness.md 766 B
- templates/idea.md 268 B
- templates/settings.json 571 B
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 Changed 3af4d909abac
- 1mo ago First seen · 399 lines · 13 tokens per session scan A 671a383363a2
self-improve is a skill published in the GitHub repository RobinNorberg/oh-my-copilot (5 stars, last pushed yesterday), licensed MIT. It adds 13 tokens to every session and 5,155 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to self-improve, differing in 34 lines, and is treated as a copy.
Other skills, from other repositories
windbg-diagnostic-method
Use with every WinDbg plugin investigation to apply evidence-first reasoning, confidence calibration, contrarian review, structured reporting, and deterministic validation. Not a bug-family-specific triage skill.
windbg-kernel-bugcheck-triage
Use when a kernel dump reports a Windows bugcheck; decode parameters and recover exception or trap context before investigating your driver. Not for user-mode process crashes or blaming a module from its name alone.
windbg-user-exception-triage
Use when a native C/C++ app, service, or user-mode driver host (including UMDF) crashes with a structured exception in a dump or WinDbg session, including native faults inside managed processes. Not for managed .NET exceptions, WinUI/XAML app errors, or kernel bugchecks.
windbg-user-heap-corruption-investigation
Use when an app, service, or user-mode driver host heap fails or Application Verifier detects corruption; inspect history and bounds. Not for kernel pool corruption or ordinary OOM.
windbg-user-virtual-memory-exhaustion
Use when a native app, service, or user-mode driver host allocation fails; distinguish VA exhaustion, fragmentation, and commit pressure. Not for managed .NET heap growth, proving a leak from one snapshot, or corruption.
windbg-kernel-irp-lifecycle-triage
Use when kernel evidence shows stalled I/O, a power IRP, or completion/cancellation misuse; inspect request state and driver ownership. Not for interpreting an empty IRP search in a limited dump as proof of healthy I/O.