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 skills add coddy-project/coddy-agent --skill rpa-gen-rulesgit clone --depth 1 https://github.com/coddy-project/coddy-agentWrote 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/skills/coddy-project/coddy-agent/rpa-gen-rules)<a href="https://agentmods.dev/skills/coddy-project/coddy-agent/rpa-gen-rules"><img src="https://agentmods.dev/badge/skills/coddy-project/coddy-agent/rpa-gen-rules/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/skills/coddy-project/coddy-agent/rpa-gen-rules"><img src="https://agentmods.dev/badge/skills/coddy-project/coddy-agent/rpa-gen-rules.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 | $0.00061 | $0.01087 |
| Opus 5.5 | $0.00024 | $0.00435 |
| Sonnet 5.5 | $0.00012 | $0.00217 |
| Haiku 4.5 | $0.00006 | $0.00109 |
Grade A, and why
rpa-gen-rules 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 11d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate project rules
Goal
Create project instructions for the coding-agent hosts the repository actually supports.
- Keep repository-wide policy in root
AGENTS.md; - enforce layered implementation from lower dependencies upward;
- require RED-GREEN-REFACTOR for behavior changes;
- use native Cursor and Claude Code formats accurately;
- let the Codex project hook attach Cursor rules without duplicating their bodies;
- never promise another host equivalent scoped delivery without a test.
Infer the contract from code, tests, docs, builds, and CI. Ask only when a real product decision is missing. Generated instruction files default to English unless the user or repository defines another language.
Read progressively
references/bdd-and-agents.md- BDD wording, host behavior, synchronization, and limitations;references/cursor-examples/.cursor/rules/andreferences/claude-examples/.claude/- native templates;references/codex-examples/.codex/hooks.jsonandhooks/attach_rules.py- Codex adapter templates.
Workflow
- Inventory root instructions, rule trees, architecture docs, tests, build files, and CI;
- choose only hosts the repository uses or the user requests;
- write architecture boundaries, real verification commands, security invariants, and documentation duties in repository terms;
- create scoped native rules without widening their activation;
- synchronize deliberate mirrors and install the Codex hook when Codex is in scope;
- run repository checks, probe adapters, verify symlinks, and report limitations honestly.
Quick reference
| Surface | Generated output | Role |
|---|---|---|
| Common | root AGENTS.md |
repository-wide baseline |
| Claude compatibility | CLAUDE.md symlink or short import |
same top-level policy |
| Cursor | .cursor/rules/*.mdc |
native Cursor rules and Codex hook input |
| Claude Code | .claude/rules/*.md |
native Claude Code rules |
| Codex | root AGENTS.md, .codex/hooks.json, .codex/hooks/attach_rules.py |
common policy plus project adapter |
| Other hosts | existing, documented integration | no invented adapter |
What ships with it
19 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- LICENSE 1.0 KB
- README.md 3.5 KB
- references/bdd-and-agents.md 8.1 KB
- references/claude-examples/.claude/CLAUDE.md 1.9 KB
- references/claude-examples/.claude/rules/api-layer.md 499 B
- references/claude-examples/.claude/rules/architecture.md 703 B
- references/claude-examples/.claude/rules/code-style.md 809 B
- references/claude-examples/.claude/rules/implementation-order.md 621 B
- references/claude-examples/.claude/rules/testing.md 814 B
- references/claude-examples/.claude/rules/workflow.md 3.4 KB
- references/codex-examples/.codex/hooks.json 930 B
- references/codex-examples/.codex/hooks/attach_rules.py 18 KB runs code
- references/cursor-examples/.cursor/rules/api-layer.mdc 1.3 KB
- references/cursor-examples/.cursor/rules/architecture.mdc 1014 B
- references/cursor-examples/.cursor/rules/code-style.mdc 2.7 KB
- references/cursor-examples/.cursor/rules/core-modules.mdc 554 B
- references/cursor-examples/.cursor/rules/implementation-order.mdc 2.1 KB
- references/cursor-examples/.cursor/rules/testing.mdc 3.4 KB
- references/cursor-examples/.cursor/rules/workflow.mdc 7.5 KB
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.
- 11d ago Changed · -108 lines · -123 tokens per session 9f53f7bed74d
- 22d ago Changed · +1 lines c4765a501374
- 1mo ago First seen · 197 lines · 184 tokens per session scan A d3f908e1c6dd
rpa-gen-rules is a skill published in the GitHub repository coddy-project/coddy-agent (175 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 1,087 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 2026-09-16.
Other skills, from other repositories
test-driven-development
Writing code with tests first: RED-GREEN-REFACTOR, reproduce bugs as failing tests before fixing, and avoid testing anti-patterns. Use when implementing behaviour, fixing a defect, or asked to add tests.
go
Go phase. Reads the approved SPEC file, maps Requirements to tasks (plan), executes via TDD (build), and integrates results verifying all Acceptance Criteria.
tdd
Test-Driven Development enforcer. Red→Green→Refactor cycle with no production code without a failing test first. Use for new features and bug fixes.
test-writer
Writes tests that fail before a fix and pass after it.
test-writing
Write tests that catch real regressions — behavior-focused, minimal mocking, edge cases chosen from the code's actual branches. Use when adding tests for new code or backfilling tests for a fix.
tdd
Test-driven development — write the failing test first, then the code. Triggers on TDD, test first, write tests, test-driven.