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 instructions/gaurav7974/agent-regress/agents-mdgit clone --depth 1 https://github.com/Gaurav7974/agent-regressWrote 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/instructions/gaurav7974/agent-regress/agents-md)<a href="https://agentmods.dev/instructions/gaurav7974/agent-regress/agents-md"><img src="https://agentmods.dev/badge/instructions/gaurav7974/agent-regress/agents-md.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 | $0.00400 | $0.00400 |
| Opus 5 | $0.00200 | $0.00200 |
| Sonnet 5 | $0.00080 | $0.00080 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
agent-regress AGENTS.md 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.
What it actually says
AGENTS.md
Repository Context
This file serves as a system prompt and context guide for any AI coding agents that open this repository.
Project: agent-regress - A local MCP server that provides tools to run regression tests against AI coding agents using deterministic code checks.
Key Directives
- Semantic Evaluation is Deferred: The current architecture intentionally defers semantic evaluation (AI-judged tests) until post-MVP. If an eval specifies
pass_criteria.type: "semantic", theexecute_evaltool must return a hardcodedSKIPPED_SEMANTIC_MVPstatus. Do not attempt to implement semantic evaluation logic. - Deterministic Checks Only: All evaluations must rely solely on standard deterministic criteria (regex, JSON schema, exit code, exact match). Do not use AI to judge tests.
- Atomic File Operations: The
.eval_history/manifest.jsonfile uses a temporary file write and a retry-based rename loop to avoid race conditions with concurrent readers on Windows. Do not simplify this logic. - Process Tree Cleanup:
execute_evalusestaskkill /F /Ton Windows and-PIDprocess group termination on Unix to prevent orphaned subprocesses during timeouts.
Build & Test Commands
- Install Dependencies:
npm install - Build:
npm run build - Run Tests:
npm run test:list-evals(list_evals)npm run test:cli-execution(CLI execution & timeouts)npm run test:http-execution(HTTP execution & schema validation)npm run test:validation-and-history(Validation logic & atomic writes)npm run test:diffing(Baseline & Regression diffing)npm test(Run all suites)
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 · 26 lines · 400 tokens per session scan A d4cd23a35e17
agent-regress AGENTS.md is an instructions file published in the GitHub repository Gaurav7974/agent-regress (0 stars, last pushed 1mo ago), licensed MIT. It adds 400 tokens to every session, about $0.0020 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 instructions, from other repositories
claude-prompts-mcp CLAUDE.md
Claude Code instructions for minipuft/claude-prompts-mcp, covering claude prompts mcp -- operator handbook, core principles, node.js support boundaries, validation gates (one contract, impact-aware subsets) and fleet standards upstream (minipuft/repository-standards).
mcp-observatory AGENTS.md
AGENTS.md instructions for KryptosAI/mcp-observatory, covering agent guide for mcp observatory, high-leverage agent tasks, avoid, useful commands and bot maintainer contribution path.
claude-prompts-mcp AGENTS.md
AGENTS.md instructions for minipuft/claude-prompts-mcp, covering agent rules · claude prompts mcp, canonical ownership and loading, core principles, node.js support boundaries and validation gates (one contract, impact-aware subsets).
pubcrawl CLAUDE.md
Claude Code instructions for nickjlamb/pubcrawl, covering claude.md, project overview, commands, testing and architecture.
gmail-mcp CLAUDE.md
Instructions for cunicopia-dev/gmail-mcp, covering gmail mcp — development guide, what it is, layout, module responsibilities and oauth model.
mcp AGENTS.md
Instructions for SpaceFrontiers/mcp, covering agents.md — space frontiers mcp server, what it does, layout, local dev and conventions.