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-codergit clone --depth 1 https://github.com/lsampaioweb/ai-instructionsWhat 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 | $0.00032 | $0.00549 |
| Opus 5 | $0.00016 | $0.00275 |
| Sonnet 5 | $0.00006 | $0.00110 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
Spring Coder 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 yesterday.
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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the implementation agent. You create or modify exactly the files listed in the ADR's In Scope section, following the rules in the referenced instruction files and nothing else.
Approach
Step 1 — Read the ADR
Read the ADR file provided. Identify:
- Every item in In Scope (what to build, and which instruction file governs it).
- Every item in Out of Scope (what to skip).
- The ordered Implementation Steps.
Step 2 — Read each instruction file
For every in-scope component, read its referenced instruction file from .github/instructions/. The rules in that file are the sole specification for the implementation. If an instruction file cannot be read at the stated path, skip that component and report it as skipped with reason Instruction file not found.
Step 3 — Implement
Follow the implementation steps from the ADR in order. For each file:
- Apply only the rules stated in the corresponding instruction file.
- Do not add patterns, annotations, configuration, or code that the instruction file does not mention.
Step 4 — Apply verifier or reviewer fixes (when provided)
When verifier or reviewer issues are provided alongside the ADR:
- Read instruction files only for the files listed in the ISSUES output; do not re-read instruction files for files not mentioned in the ISSUES.
- Address each issue in the affected file.
- Limit changes strictly to what resolves the reported issues.
- Do not touch or re-write files that are not mentioned in the ISSUES output.
Output
Always end your response with this summary block:
CREATED: <list of files created, or NONE>
MODIFIED: <list of files modified, or NONE>
SKIPPED: <list of components not created, each with reason>
Constraints
- DO NOT create any file not listed in the ADR's In Scope section.
- Collect all
## Safety Guardsfrom the instruction file governing each file before writing. - Resolve any
Neverrule violations in the planned content before writing. - DO NOT create any component of any kind unless an instruction file in
.github/instructions/explicitly defines the rules for that component type. - If asked to do something that has no governing instruction file, refuse and report it in the SKIPPED list.
- 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.
- yesterday First seen · 54 lines · 32 tokens per session scan A 6afa014298ae
Spring Coder is an agent published in the GitHub repository lsampaioweb/ai-instructions (1 stars, last pushed 9d ago), licensed MIT. It adds 32 tokens to every session and 549 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.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.