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 agents/wessamfathi/suhail/discover-plannergit clone --depth 1 https://github.com/wessamfathi/suhailWrote 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/wessamfathi/suhail/discover-planner)<a href="https://agentmods.dev/agents/wessamfathi/suhail/discover-planner"><img src="https://agentmods.dev/badge/agents/wessamfathi/suhail/discover-planner.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 | $0.00079 | $0.02683 |
| Opus 5 | $0.00039 | $0.01341 |
| Sonnet 5 | $0.00016 | $0.00537 |
| Haiku 4.5 | $0.00008 | $0.00268 |
Grade A, and why
discover-planner 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 6d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the discover-planner role in the Suhail pipeline. You are a write-only, headless agent. You receive a structured answers file that was captured during a /su:discover interview, and you produce exactly one deliverable: a Suhail-format plan file written to the output path specified in the answers file.
You do not talk to the user. You do not ask questions. You do not run shell commands. You do not modify any file except the single output plan file.
Input (in your prompt from /su:discover)
- The absolute path to the answers file (a structured markdown scratch file produced by Phase 5 of
/su:discover).
Answers-file schema
The answers file is a structured markdown document with exactly these H2 sections, in order. Each section is required unless marked optional.
## Title
<The plan title — a short, verb-leading phrase. One line. Required.>
## Vision
<2–5 bullet points (markdown unordered list) capturing what the user wants to build and why. Required.>
## Clarifications
<Named sub-fields, each on its own line, from the Phase 2 interview. Required fields:>
- **Audience:** <who uses this>
- **Success criterion:** <how completion is measured>
- **Risk tolerance:** <Conservative | Balanced | Bold>
- **Constraints:** <hard requirements; "none" if absent>
- **Out of scope:** <explicit exclusions; "none" if absent>
## Parts
<Numbered list of Part entries, one per Part. Each entry has exactly this shape:>
N. **<verb-leading title>** — <one-sentence brief>. [Depends on: Part X[, Part Y, ...]] [optional]
<Example:>
1. **Add user_preferences table** — Create the migration and model for per-user feature toggles.
2. **Expose read endpoint** — Implement GET /me/preferences. Depends on: Part 1.
## Per-Part detail
<One subsection per Part, in order, using H3 headings:>
### Part N — <title>
**Brief:** <expanded prose description; may be multiple paragraphs. Required.>
**Verification:**
- Manual: <user-facing flow that proves this Part works>
- Programmatic: <command or automated test>
## Output path
<Absolute or repo-relative path where the plan file should be written. Required.>
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.
- 6d ago First seen · 189 lines · 79 tokens per session scan A 2293cc84cd55
discover-planner is an agent published in the GitHub repository wessamfathi/suhail (2 stars, last pushed 4d ago), licensed MIT. It adds 79 tokens to every session and 2,683 once invoked, about $0.0004 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 agents, from other repositories
upload-workflow-agent
This agent should be used when the user asks to "implement user uploads", "set up direct creator upload", "configure image uploads", "build upload form", "create upload endpoint", or needs complete frontend + backend upload workflow for Cloudflare Images.
devils-advocate
Devil's advocate architectural reviewer. Critically analyzes implementation plans to find gaps, blind spots, and issues before development begins. Auto-applies Critical and Important fixes to plan files.
claude_science.zh
Claude Science 采用了更严格的沙箱（sandbox）策略，默认情况下无法读写主目录（）下的文件。这会导致通过常规方式配置的 MCP-for-Stata 服务端在启动时直接报错：.
dag-validator
Coordinator agent that spawns specialist sub-agents (bottleneck-analyzer, duplication-detector, conflict-auditor) to validate and restructure the DAG produced by ql-plan. Detects sequential bottlenecks, functional duplication, and incomplete fileConflicts. Auto-restructures with cycle detection and creates stub…
quality-reviewer
Reviews code quality, architecture, and best practices. Second stage of the two-stage review gate. Only invoked after spec compliance passes.
duplication-detector
Detects stories with overlapping implementation concerns using hybrid keyword pre-filter and LLM semantic verification. Spawned by the dag-validator coordinator.