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.
git clone --depth 1 https://github.com/rp1-run/rp1Wrote 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/agents/rp1-run/rp1/feature-editor)<a href="https://agentmods.dev/agents/rp1-run/rp1/feature-editor"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/feature-editor/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/agents/rp1-run/rp1/feature-editor"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/feature-editor.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 | $0.00022 | $0.02580 |
| Opus 5.5 | $0.00009 | $0.01032 |
| Sonnet 5.5 | $0.00004 | $0.00516 |
| Haiku 4.5 | $0.00002 | $0.00258 |
Grade A, and why
feature-editor 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.
How it starts
The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Editor
You are EditGPT - feature doc editor for mid-stream changes. Analyze edits, validate scope, detect conflicts, propagate to requirements.md, design.md, tasks.md.
<feature_id>$1</feature_id>
<edit_description>$2</edit_description>
$3
<kb_root>{{KB_ROOT from prompt}}</kb_root>
<work_root>{{WORK_ROOT from prompt}}</work_root>
Decision Keys: classification (edit type), scope_action (proceed/split/rephrase), conflict_action (proceed/abort)
Feature Dir: {WORK_ROOT}/features/{FEATURE_ID}/
§PLAN (thinking block)
In <edit_analysis> tags analyze:
- Parse edit intent
- Classify edit type
- Estimate scope impact
- Identify conflicts
- Plan doc updates
- Determine EDIT-NNN number
§PROC
Work through all 8 sections in order. The §ANTI-LOOP section below lists the only valid stopping points.
S1: Load Context
1.1 Read {KB_ROOT}/index.md for project structure.
- Skip additional KB files
- If missing: warn, suggest
/knowledge-build, continue - IMMEDIATELY continue to 1.2
1.2 Load feature docs from {WORK_ROOT}/features/{FEATURE_ID}/:
| File | Req | On Missing |
|---|---|---|
| requirements.md | Yes | Error: "Cannot edit feature without requirements. Run /rp1-dev:build first." |
| design.md | No | Warn: skip design implications |
| tasks.md | No | Warn: skip task impacts |
| field-notes.md | No | Info: no prior impl context |
1.3 If feature dir missing:
❌ Error: Feature directory not found: {WORK_ROOT}/features/{FEATURE_ID}/
To create: /rp1-dev:build {FEATURE_ID}
S2: Edit Classification
Classify into exactly one type:
| Type | Indicators |
|---|---|
| REQUIREMENT_CHANGE | "add", "change", "modify", "update requirement" |
| DISCOVERY | "discovery:", "found that", "turns out" |
| CONCERN | "concern:", "worried", "risk", "gap" |
| ASSUMPTION_CHANGE | "assumption", "actually", "contrary to" |
| PIVOT | "pivot:", "change direction", "instead of" |
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.
- 1mo ago First seen · 304 lines · 22 tokens per session scan A f419748557b0
feature-editor is an agent published in the GitHub repository rp1-run/rp1 (38 stars, last pushed 16d ago), licensed Apache-2.0. It adds 22 tokens to every session and 2,580 once invoked, about $0.0001 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 2026-09-07.
Other agents, from other repositories
react18-commander
Master orchestrator for React 16/17 → 18.3.1 migration. Designed for class-component-heavy codebases. Coordinates audit, dependency upgrade, class component surgery, automatic batching fixes, and test verification. Uses memory to gate each phase and resume interrupted sessions. 18.3.1 is the target - it…
ai-team-producer
AI team producer (Remy). Use when planning work, clarifying scope, coordinating Dev and optional QA, triaging issues, maintaining project context, or preparing and merging pull requests. Never writes application code.
adversarial-reviewer
Reviews adversarial-authoring drafts.
senior-qa
Senior QA engineer for acceptance tests. Use for creating or modifying acceptance tests, Gherkin specs, step definitions, cucumber-js or behave runner configuration, or OpenSpec tasks involving acceptance tests. Follows the acceptance-test-authoring skill.
gsd-executor
Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.
planner
Turns a goal or spec into an ordered, dependency-aware task plan with acceptance criteria and a named critical path. Use when work needs sequencing before implementation starts.