agentmods.dev

promptrejectormcp: Instructions file for Codex

AGENTS.md

promptrejectormcp AGENTS.md is an instructions file for Codex, OpenCode from revsmoke/promptrejectormcp. It costs 739 tokens per session, scanned A, original, ISC.

Repository instructions for a prompt-rejection project, including its file map, operations guides, configuration notes, plugin documentation, and release process.

In plain words
What is it for?
Use them to understand the project layout and find the instructions for development, operations, plugins, and releases.
Why use it?
They point a coding agent to the right documents and constraints before it changes the repository.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is revsmoke/promptrejectormcp's own configuration. It tells Codex and OpenCode how to work on promptrejectormcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything promptrejectormcp configures →

not rated 2repo changed 1mo ago A scan 739 tokens original ISC
View source ↗ revsmoke/promptrejectormcp
Reuse

Borrowing it

Nothing to install: this file belongs to revsmoke/promptrejectormcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/revsmoke/promptrejectormcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/revsmoke/promptrejectormcp

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for promptrejectormcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/revsmoke/promptrejectormcp/agents-md/github.svg)](https://agentmods.dev/instructions/revsmoke/promptrejectormcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/revsmoke/promptrejectormcp/agents-md"><img src="https://agentmods.dev/badge/instructions/revsmoke/promptrejectormcp/agents-md/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.

agentmods 80×15 button for promptrejectormcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/revsmoke/promptrejectormcp/agents-md"><img src="https://agentmods.dev/badge/instructions/revsmoke/promptrejectormcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 739 This file is loaded in full into every session.
When invoked 739 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00739 $0.00739
Opus 5.5 $0.00296 $0.00296
Sonnet 5.5 $0.00148 $0.00148
Haiku 4.5 $0.00074 $0.00074

Measured 1mo ago against content hash a295de17f642, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

promptrejectormcp 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 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.

AGENTS.md · 29 lines

How it starts

The opening of the file, as written. The whole thing — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository guide

Resources

  • README.md: installation, current endpoints, MCP setup and command reference; docs/cli.md: CLI, JSONL automation, exit codes and typed SDK.
  • CONTRIBUTING.md: offline development and contributor tasks; SECURITY.md: private vulnerability reporting; .github/ISSUE_TEMPLATE/: report forms.
  • docs/operations/local-server.md: installed service/worktree paths, HTTPS certificates and restart procedure. Check here before changing a running service.
  • config/README.md, docs/operations/ai-models.md: active configuration, provider roles, model switching and access probes.
  • docs/how-we-use-jev-from-typesafe-ai.md: TypeSafe design and measured results; docs/operations/typesafe-rollout.md: modes and bounded live tests.
  • docs/plugins.md: installation; plugins/prompt-rejector/: manifests, setup skill and launchers; scripts/build-plugins.mjs: packaging.
  • docs/feature-reference.md: other detectors/feeds; CONTRIBUTING.md#release--publishing: release/version procedure.
  • docs/specs/, docs/superpowers/plans/, docs/implementation/typesafe-progress.md: design and delivery history. Root SPEC.md/PLAN.md describe v1.1; earlier off-by-default and dual-API plans are superseded.
  • experiments/typesafe/results/, evaluations/ai/runs/: saved evidence; development results are not held-out qualification.

Code map

  • src/bootstrap.ts: shared service wiring; src/api/ and src/mcp/: transports; src/client/: typed operation boundary; src/cli/: executable, bounded input and streaming JSONL.
  • src/services/: scanners, DecisionPolicy.ts, AnalysisCoverage.ts, JudgmentService.ts and JudgmentCache.ts.
  • src/ai/: provider contracts/adapters, versioned questions (rubrics/), configuration, budgets and usage; src/schemas/: report validation.
  • patterns/: detection library/manifest; src/services/PatternService.ts: integrity and updates.

Easy-to-miss constraints

  • REST is HTTPS on local port 3001, /v2 only; /v1 returns 410. MCP has no version selector. Use dedicated src/scripts/start*.ts launchers; stdio clients invoke compiled Node entrypoints directly, not npm's stdout banners.
  • Launchers select config/ai.active.json unless overridden; low-level environment-only defaults differ. Model changes require restart/reconnection.
  • Only decision: "allow" means safe. Prompt/skill cascades may skip reasoning after a conclusive block, never because Jev scores are low. Missing analysis is not a benign result. Policy lives in DecisionPolicy.ts.
  • Package root imports the SDK without startup; CLI uses dist/cli/main.js. Reserve CLI stdout for JSON. Only scan exit 0/explicit allow authorizes processing; block/review=1, bad input=2, ordinary unavailable/operational error=3, timeout=124, SIGINT/SIGTERM=130/143. Test installed artifacts with npm run test:cli-package.
  • Use npm run test:offline (builds, isolates suites, guards network); npm test is an incomplete legacy chain. Register offline suites in src/scripts/runOfflineTests.ts. Plugin tests: npm run test:plugins.

Read the full file on GitHub · 29 lines

Changes

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.

  1. 1mo ago Changed · +1 lines · +124 tokens per session a295de17f642
  2. 1mo ago First seen · 28 lines · 615 tokens per session scan A 7d5cc2424a47

Subscribe to this mod's changes

promptrejectormcp AGENTS.md is an instructions file published in the GitHub repository revsmoke/promptrejectormcp (2 stars, last pushed 1mo ago), licensed ISC. It adds 739 tokens to every session, about $0.0030 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 2026-09-22.

Claude Codeai-securityclaudecybersecuritygeminillm-safety
Related

promptrejectormcp AGENTS.md compared with instructions from other repositories

promptrejectormcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
promptrejectormcp AGENTS.mdrevsmoke/promptrejectormcpInstructions file21mo agoISCA739Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot