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/nitinjain999/platform-skillsnpx agentmods add commands/nitinjain999/platform-skills/self-improveWrote 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/nitinjain999/platform-skills/self-improve)<a href="https://agentmods.dev/commands/nitinjain999/platform-skills/self-improve"><img src="https://agentmods.dev/badge/commands/nitinjain999/platform-skills/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/commands/nitinjain999/platform-skills/self-improve"><img src="https://agentmods.dev/badge/commands/nitinjain999/platform-skills/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 | $0.00137 | $0.05167 |
| Opus 5 | $0.00068 | $0.02583 |
| Sonnet 5 | $0.00027 | $0.01033 |
| Haiku 4.5 | $0.00014 | $0.00517 |
Grade B, and why
self-improve scanned grade B with 1 finding 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 9d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
5. Detect the user's platform and offer to wire all three hooks in `~/.claude/settings.json`: How it starts
The opening of the file, as written. The whole thing — 435 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bootstrap and operate a self-improving, proactive agent workspace.
Path Resolution (applies to all modes)
Before executing any mode, resolve LEARNINGS_BASE:
- If mode is
init global→ use~/.claude/ - Else if mode is
init local→ use.(current working directory) - Else if
~/.claude/.learnings/exists → use~/.claude/as base (global setup) - Else if
.learnings/exists in the current working directory → use.as base (project setup) - Else if mode is
init(no argument) → ask the user to choose (see init mode below) - Else → default to
~/.claude/, create the directories, and inform the user that global setup was auto-created
~/.claude/ resolves consistently across all platforms (macOS, Linux, Windows) because Claude Code uses os.homedir() for ~. On Windows this maps to C:\Users\<you>\.claude\ — no manual path adjustment needed.
All path references in every mode below use LEARNINGS_BASE as the root:
| Logical path | Resolved path (global) | Resolved path (project) |
|---|---|---|
.learnings/LEARNINGS.md |
~/.claude/.learnings/LEARNINGS.md |
.learnings/LEARNINGS.md |
.learnings/ERRORS.md |
~/.claude/.learnings/ERRORS.md |
.learnings/ERRORS.md |
.learnings/FEATURE_REQUESTS.md |
~/.claude/.learnings/FEATURE_REQUESTS.md |
.learnings/FEATURE_REQUESTS.md |
memory/working-buffer.md |
~/.claude/memory/working-buffer.md |
memory/working-buffer.md |
memory/SESSION-STATE.md |
~/.claude/memory/SESSION-STATE.md |
memory/SESSION-STATE.md |
memory/YYYY-MM-DD.md |
~/.claude/memory/YYYY-MM-DD.md |
memory/YYYY-MM-DD.md |
.learnings/.pending-errors.log |
~/.claude/.learnings/.pending-errors.log |
.learnings/.pending-errors.log |
Promotion targets (CLAUDE.md, AGENTS.md, .github/copilot-instructions.md) always remain project-local regardless of scope — only the capture files follow LEARNINGS_BASE.
Reference: references/agent-self-improve.md → Global vs project scope
Mode: init global
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.
- 9d ago First seen · 435 lines · 137 tokens per session scan B d263f3b10233
self-improve is a command published in the GitHub repository nitinjain999/platform-skills (41 stars, last pushed yesterday), licensed Apache-2.0. It adds 137 tokens to every session and 5,167 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
ia-compound-refresh
Review docs/solutions/ for stale learnings -- keep, update, replace, or archive.
ia-compound
Parallel-agent workflow to document a solved problem for team reuse. Use after debugging, fixing, or resolving a bug, incident, or tricky edge case worth capturing for future sessions.
promote
Move .memory/ artifacts to permanent knowledge locations.
checkpoint
Create or update .memory/ with current conversation state.
cleanup
Delete promoted content from the .memory/ directory.
memory-graph
Open the memory graph visualization in your browser.