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/krgoodnews/pedal/agents-mdgit clone --depth 1 https://github.com/krgoodnews/PEDALWrote 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/krgoodnews/pedal/agents-md)<a href="https://agentmods.dev/instructions/krgoodnews/pedal/agents-md"><img src="https://agentmods.dev/badge/instructions/krgoodnews/pedal/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 | $0.00271 | $0.00271 |
| Opus 5 | $0.00135 | $0.00135 |
| Sonnet 5 | $0.00054 | $0.00054 |
| Haiku 4.5 | $0.00027 | $0.00027 |
Grade A, and why
PEDAL 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
Agent Instructions
PEDAL workflow
When the user mentions PEDAL, planning, engineering documents, gap analysis, iteration, completion reports, or asks for plan, engineering, do, analyze, iterate, learn, archive, status, next, spec, build, or dev, read and follow .pedal/PEDAL.md.
PEDAL is tool-agnostic. Do not assume Gemini-only slash commands are required. If this agent does not support slash commands, treat natural language requests such as PEDAL plan A_Project user-auth as the equivalent PEDAL action.
Key rules:
- Run PEDAL from the workspace root that contains the project repositories.
- Use git worktrees for feature work as described in
.pedal/PEDAL.md. - After creating a feature worktree, perform feature-specific file operations inside that worktree, not the main project directory.
- Infer PEDAL status from worktree and
docs/files; do not create a separate state file. - During Plan, Engineering, Do, and Analyze phases, read
docs/wiki/CONVENTIONS.mdif it exists. - Keep tool-specific behavior in the relevant adapter file. The shared workflow source of truth is
.pedal/PEDAL.md.
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 · 17 lines · 271 tokens per session scan A 3e07403fa27e
PEDAL AGENTS.md is an instructions file published in the GitHub repository krgoodnews/PEDAL (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 271 tokens to every session, about $0.0014 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
camunda load-tests.instructions.md
Instructions for camunda/camunda, covering load test review guidelines, required review checks, what gets backported, documentation and scheduled release load tests.
STAR AGENTS.md
AGENTS.md instructions for wanghao9610/STAR, covering agent instructions, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.
airflow CLAUDE.md
Claude Code instructions for apache/airflow, a project described as: Apache Airflow - A platform to programmatically author, schedule, and monitor workflows.
usurahi CLAUDE.md
Instructions for usurahi-project/usurahi, covering 薄氷（うすらひ）— 共通ガイド, 薄氷とは, 共通原則, 会議状態の最小定義 and 起動時.
gza CLAUDE.md
Claude Code instructions for mhawthorne/gza: Read AGENTS.md for all project instructions.
superpowers-graph CLAUDE.md
Claude Code instructions for RonMizrahi/superpowers-graph, covering superpowers-graph — repository guide, sources of truth, changing the graph — the eval ships with the change and rules that are not obvious from the code.