Borrowing it
Nothing to install: this file belongs to andreaswasita/copilot-agents-dojo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/andreaswasita/copilot-agents-dojo/main/.github/prompts/dojo-self-improvement.prompt.mdgit clone --depth 1 https://github.com/andreaswasita/copilot-agents-dojoWrote 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/commands/andreaswasita/copilot-agents-dojo/dojo-self-improvement)<a href="https://agentmods.dev/commands/andreaswasita/copilot-agents-dojo/dojo-self-improvement"><img src="https://agentmods.dev/badge/commands/andreaswasita/copilot-agents-dojo/dojo-self-improvement/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/commands/andreaswasita/copilot-agents-dojo/dojo-self-improvement"><img src="https://agentmods.dev/badge/commands/andreaswasita/copilot-agents-dojo/dojo-self-improvement.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 | $0.00008 | $0.00109 |
| Opus 5.5 | $0.00003 | $0.00044 |
| Sonnet 5.5 | $0.00002 | $0.00022 |
| Haiku 4.5 | $0.00001 | $0.00011 |
Grade A, and why
dojo-self-improvement 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 1mo 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
Activate the self-improvement dojo skill.
Read skills/self-improvement/SKILL.md in full, then apply its procedure to the current request. Honour its When to Use, Procedure, Pitfalls, and Verification sections — do not skip the verification step.
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.
- 1mo ago First seen · 10 lines · 8 tokens per session scan A 99d4678a88ac
dojo-self-improvement is a command published in the GitHub repository andreaswasita/copilot-agents-dojo (54 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 109 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-09-07.
Other commands, from other repositories
save-session
Save current session state to a dated file in /.claude/sessions/ so work can be resumed in a future session with full context.
pull-learnings
Pulls shared organization patterns into local org-patterns.toon.
context-stats
Display context window usage and token statistics.
handoff-context
Generate context handoff and copy to clipboard for new session - preserves decisions, progress, and next steps across conversations.
context
You are the Context Manager, responsible for monitoring and optimizing context usage during long implementation sessions. You help prevent context overflow and maintain efficiency.
lessons
Lists the feedback memories captured for the current project (and globally) — the "lessons" learned from user corrections.