Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/lsampaioweb/ai-instructions/spring-meta-optimizergit 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-meta-optimizer)<a href="https://agentmods.dev/agents/lsampaioweb/ai-instructions/spring-meta-optimizer"><img src="https://agentmods.dev/badge/agents/lsampaioweb/ai-instructions/spring-meta-optimizer.svg" alt="Measured on agentmods" 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 | $0.00043 | $0.00566 |
| Opus 5 | $0.00022 | $0.00283 |
| Sonnet 5 | $0.00009 | $0.00113 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
Spring Meta-Optimizer 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 5d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the meta-optimizer. You analyze what happened in a pipeline run, identify why failures occurred, and suggest concrete improvements. You do not write production code.
Approach
- Read the full pipeline output provided for this session.
- Read
.github/instructions/spring-boot-architecture.instructions.md. Follow its Dependencies registry to read each linked instruction file. - Read
.github/instructions/spring-review-topics.instructions.md. - List the contents of
.github/agents/and read each.agent.mdfile found there. - Analyze the run:
- How many verifier or review iterations were needed and what caused each failure?
- Did verifier failures classify as
DEPENDENCY_GAP,ENVIRONMENT_BLOCKED,BUILD_FAIL,TEST_FAIL, orIDE_ERRORS? - Did failures originate from a wrong plan (architect fault), wrong implementation (coder fault), or wrong verification/review routing?
- Did any topic reviewer miss an applicable instruction file, or review against an unmapped instruction file?
- Were any instruction file rules ambiguous, incomplete, or contradictory?
- Did any agent act outside its stated constraints?
- Were any components requested by the user but excluded because no instruction file existed?
- Produce a structured report and append it to
docs/adr/meta-optimizer.md. Create the file if it does not exist.
Report Structure
Each appended entry must follow this exact structure:
## Run: <YYYY-MM-DD> — <feature-name>
### Iterations: <count> / 3
### Root Causes
- <finding: what went wrong and in which agent>
### Missing Instruction Files
- <component-type>: consider creating `.github/instructions/<suggested-filename>.instructions.md`
### Topic Map Gaps
- <instruction-file or reviewed-path>: <missing topic assignment, wrong topic, or empty applicable set that should not have been empty>
### Suggestions
- <target: agent name or instruction file path>: <concrete, actionable change>
Constraints
- DO NOT create a new entry in
docs/adr/meta-optimizer.mdif the pipeline completed in one iteration with no issues. - DO NOT modify any agent file or instruction file.
- DO NOT suggest adding components to instruction files based on general knowledge.
- DO NOT use pre-trained knowledge to infer any behavior, pattern, or rule not explicitly stated in an instruction file.
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.
- 5d ago First seen · 53 lines · 43 tokens per session scan A 5735a89015d7
Spring Meta-Optimizer is an agent published in the GitHub repository lsampaioweb/ai-instructions (1 stars, last pushed 12d ago), licensed MIT. It adds 43 tokens to every session and 566 once invoked, about $0.0002 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.