Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/andreaswasita/copilot-agents-dojonpx agentmods add skills/andreaswasita/copilot-agents-dojo/self-improvementWrote 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/andreaswasita/copilot-agents-dojo/self-improvement)<a href="https://agentmods.dev/skills/andreaswasita/copilot-agents-dojo/self-improvement"><img src="https://agentmods.dev/badge/skills/andreaswasita/copilot-agents-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/skills/andreaswasita/copilot-agents-dojo/self-improvement"><img src="https://agentmods.dev/badge/skills/andreaswasita/copilot-agents-dojo/self-improvement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 64 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00012 | $0.02141 |
| Opus 5 | $0.00006 | $0.01071 |
| Sonnet 5 | $0.00002 | $0.00428 |
| Haiku 4.5 | $0.00001 | $0.00214 |
Grade A, and why
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 10d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Improvement Skill
Logs every correction and failed approach to tasks/lessons.md with structured metadata, escalates recurring patterns into skill amendments via scripts/lesson-updater.sh, and respects the cache-aware mutation rule so amendments don't trash Copilot's prompt cache mid-session. Does NOT delete or rewrite past lessons — history is evidence, not noise.
The memory vault (memory/) extends this with structured, linked knowledge:
- Lessons live in
tasks/lessons.md(short-term capture) - Patterns graduate to
memory/patterns/when they hit 3+ occurrences - Decisions are recorded in
memory/decisions/for architectural context - Preferences accumulate in
memory/preferences/from user corrections - Sessions are summarized in
memory/sessions/with links to all of the above
When to Use
- Session start: Review
memory/INDEX.md+tasks/lessons.mdbefore doing anything else - After any correction: User points out a mistake or a better approach
- After a failed approach: Something you tried didn't work
- Pattern recognition: You notice you've made a similar mistake before
- Skill amendment: A pattern hits 3+ occurrences
- After any architectural decision: Record it in
memory/decisions/ - Session end: Write a session summary in
memory/sessions/
Prerequisites
tasks/lessons.mdexists (created byscripts/init.sh).scripts/lesson-updater.shavailable for the pattern-scan + amendment proposal.- Familiarity with the cache-aware mutation rule (see
AGENTS.md→ Cache-Aware Mutations).
Before any work begins:
- Read
memory/INDEX.md— understand what knowledge exists - Read
tasks/lessons.md— check for recent, un-promoted lessons - Query relevant context:
bash scripts/memory-query.sh --type pattern --tag <current-task-domain> - Filter for entries relevant to the current project, language, or task type
- Internalize active rules — these are your guardrails for this session
- Note any lessons with high occurrence counts — these are your blind spots
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.
- 10d ago First seen · 172 lines · 12 tokens per session scan A 434e2cfefba8
self-improvement is a skill published in the GitHub repository andreaswasita/copilot-agents-dojo (53 stars, last pushed 3d ago), licensed MIT. It adds 12 tokens to every session and 2,141 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
memory-orchestrator
Implementation of the "Five-Layer Memory Reliability Pattern" (arXiv/OpenSpace Inspired). Covers observer-reflector-recovery-watcher-safeguard pipelines for cost-efficient AI agents. This skill implements the project's Memory and Cost Policy.
session-grounding
A session-start procedure for checking the current facts, scope, and work track in a governed project before taking action.
semantix
Install and use the semantix memory kernel as a middleware in your agent: extract user preferences / workflows / experience from past sessions, retrieve and inject them on demand. One binary + your agent's own tools.
save-progress
Save current project task progress to local task state file for cross-session continuity. Use when the user asks to save progress, uses an equivalent localized trigger phrase, the session is interrupted, or the user wants to resume work later. Writes to .claude/project-task-state.json so next session can load it via…
context-budget
Use when a long-horizon task is filling the context window and you must decide what to keep, offload, drop, or hand off to a fresh window — when to compact, what the summary must preserve, and whether to isolate a read-heavy subtask in a subagent. NOT dollar spend or caps (that is cost-tracking), NOT finding context…
continuous-learning
Use when a mistake, correction, or surprise taught the workspace something that must stick — a retro or postmortem, the same agent error corrected twice, a resolved bug's root cause, scattered notes-to-self — and route that lesson to the durable surface that fires next time. NOT a forward choice with alternatives…