Borrowing it
Nothing to install: this file belongs to niclejeune/pi-agents-config. 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/niclejeune/pi-agents-config/main/.pi/agent/skills/self-improve/SKILL.mdgit clone --depth 1 https://github.com/niclejeune/pi-agents-configWrote 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/niclejeune/pi-agents-config/self-improve)<a href="https://agentmods.dev/skills/niclejeune/pi-agents-config/self-improve"><img src="https://agentmods.dev/badge/skills/niclejeune/pi-agents-config/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/niclejeune/pi-agents-config/self-improve"><img src="https://agentmods.dev/badge/skills/niclejeune/pi-agents-config/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 | $0.00058 | $0.00944 |
| Opus 5 | $0.00029 | $0.00472 |
| Sonnet 5 | $0.00012 | $0.00189 |
| Haiku 4.5 | $0.00006 | $0.00094 |
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 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Improve
Reflect on the current session, identify concrete improvements, present them for approval, then create todos and execute.
Step 1: Gather Context
Use what's already in the conversation — tool outputs, errors, subagent summaries, dev server logs, test results. You're in the session, so you have the context.
Only use the session-reader skill if you need to review a subagent's session that isn't summarized in the current conversation.
Step 2: Analyze Improvement Areas
Examine each area below. Skip areas with no findings — only report what's actionable.
| Area | What to Look For |
|---|---|
| Agent config | Could AGENTS.md instructions be clearer? Did the agent misunderstand something that better wording would prevent? |
| Subagent behavior | Did subagents struggle, go off-scope, or need repeated correction? Would better task descriptions or agent definitions help? |
| Agent definitions | Check ~/.pi/agent/agents/*.md — are model choices, skills, or system prompts optimal for what was observed? |
| Tests | Were bugs found that tests should catch? Are existing tests stale or missing coverage for touched code? |
| Documentation | Are READMEs, inline docs, or references out of date after changes made this session? |
| Scripts | Did any scripts fail, produce wrong output, or need manual workarounds? |
| Extensions & MCP | Were MCP servers or extensions used that could be better configured? Were tools missing that would have helped? |
| Skills | Did any skill produce suboptimal results? Are trigger descriptions accurate? Would a new skill help? |
| Code quality | Did the session reveal patterns worth refactoring, error handling gaps, or repeated boilerplate? |
| Workflow | Were there unnecessary back-and-forth cycles, wasted API calls, or inefficient tool usage patterns? |
Step 3: Determine Scope
For each finding, classify its scope:
| Scope | Where It Lives | Example |
|---|---|---|
| Global | ~/.pi/agent/ (AGENTS.md, skills, agents) |
"Subagent worker should always run tests before committing" |
| Project | Project's .claude/, CLAUDE.md, or codebase |
"Add integration test for the auth endpoint we just fixed" |
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 · 89 lines · 58 tokens per session scan A d5eba89f8815
self-improve is a skill published in the GitHub repository niclejeune/pi-agents-config (1 stars, last pushed 4mo ago), licensed MIT. It adds 58 tokens to every session and 944 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
exa-research-planner
Plan, draft, and execute Exa deep-research workflows. Use when the user wants staged research planning, cost-aware discovery before deep synthesis, or an explicit deep-research report. Also use when the user asks to refine a research question, compare options, explore a market or technical landscape, gather sources…
brpr
(devtools plugin) Create a branch, commit changes, push, and open a PR — or just commit+push+PR if already on a feature branch. Links related issues from GitHub or Linear based on project tracker config.
workspace-explorer
Explore and navigate Notion workspaces via MCP. Use when searching for pages, understanding database structure, finding content, creating or updating pages/databases, or managing Notion workspace content. Triggers when user asks about Notion, mentions Notion pages/databases, wants to find something in their wiki…
merge
Merge or squash-merge a pull request and report best-effort remote and local source-branch cleanup. Use when user says "merge this PR", "squash merge", "md", "smd", or anything about merging pull requests.
release
Automate the release process. Use when user says "cut a release", "new version", "bump version", "publish release", or anything about versioning and publishing.
setup-oauth
Guide the user through setting up Notion MCP with OAuth authentication.