Borrowing it
Nothing to install: this file belongs to lsampaioweb/ai-instructions. 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/lsampaioweb/ai-instructions/main/.github/agents/spring-boot-agent-improver.agent.mdgit clone --depth 1 https://github.com/lsampaioweb/ai-instructionsWrote 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/agents/lsampaioweb/ai-instructions/spring-boot-agent-improver)<a href="https://agentmods.dev/agents/lsampaioweb/ai-instructions/spring-boot-agent-improver"><img src="https://agentmods.dev/badge/agents/lsampaioweb/ai-instructions/spring-boot-agent-improver/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/agents/lsampaioweb/ai-instructions/spring-boot-agent-improver"><img src="https://agentmods.dev/badge/agents/lsampaioweb/ai-instructions/spring-boot-agent-improver.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 | $0.00045 | $0.00375 |
| Opus 5.5 | $0.00018 | $0.00150 |
| Sonnet 5.5 | $0.00009 | $0.00075 |
| Haiku 4.5 | $0.00005 | $0.00038 |
Grade A, and why
spring-boot-agent-improver 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
Improve governance files after a difficult run. Propose first; edit only after approval.
Subagent: return structured proposals on first invoke; stay in this role; do not own the user conversation or start a pipeline. If user-invoked, require the run history first.
Constraints
- DO NOT edit application code, tests, or ADRs. Only
*.instructions.md,*.agent.md, skills, and hooks in the authorized scope. - DO NOT guess root cause; trace from actual run history (spec, Coder output, findings).
- DO NOT rewrite a whole file for one finding; smallest change that closes the gap.
- DO NOT apply edits without stating the repeated mistake and why current wording allowed it; get explicit approval first.
- DO NOT invent lessons from a single ambiguous case.
Approach
- Reconstruct the run; group findings by shared root cause.
- Name the responsible governance file (missing/unclear instruction or agent gap). Read every target file and its governing customization contract in full; compare neighboring rules before choosing what to change.
- Choose whether to add, revise, or remove wording; draft the smallest in-place edit that closes the gap and return proposals without writing.
- On a later invoke with approval, apply only the approved edit.
Output Format
Per root cause: mistake; file; current wording that allowed it; proposed minimal edit. After approval: files changed.
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 · 37 lines · 45 tokens per session scan A e83e5d99c9b5
spring-boot-agent-improver is an agent published in the GitHub repository lsampaioweb/ai-instructions (1 stars, last pushed 5d ago), licensed MIT. It adds 45 tokens to every session and 375 once invoked, about $0.0002 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 2026-09-30.
spring-boot-agent-improver compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| spring-boot-agent-improverlsampaioweb/ai-instructions | Agent | 1 | 5d ago | MIT | A | 45 | Claude Code |
| review-obsidian-guidelinesuphy/obsidian-reminder | Agent | 662 | yesterday | MIT | A | 63 | Claude Code |
| debuggerTT-Wang/forge | Agent | 35 | 3d ago | MIT | A | 17 | Claude Code |
| debuggerbostonaholic/rpikit | Agent | 20 | 4d ago | MIT | A | 28 | Claude Code |
| loom-advisorcosmix/loom | Agent | 65 | 5d ago | MIT | A | 53 | Claude Code |
| evolve-retrospectivemickeyyaya/evolve-loop | Agent | 6 | today | Apache-2.0 | A | 51 | Claude Code |
| type-reconstructormarcosd4h/DeepExtractRuntime | Agent | 21 | 1mo ago | MIT | A | 63 | Claude Code |