sf-scout

sf-scout is an agent for coding agents from shipfast-ai/shipfast. It costs 27 tokens per session (1,323 once invoked), scanned A, original, MIT.

A reconnaissance role that searches a codebase to find every file and connection involved in a task. Reconnaissance means gathering the relevant facts before implementation begins.

In plain words
What is it for?
Use it to trace a feature through frontend and backend code, follow imports and calls, locate state and API connections, and inspect related repositories or runtime boundaries.
Why use it?
It reduces the chance of missing a caller, user-interface entry point, state store, API route, service, or database layer that the change depends on.

Agent

Install

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.

agentmods
npx agentmods add agents/shipfast-ai/shipfast/scout
Clone the repo
git clone --depth 1 https://github.com/shipfast-ai/shipfast

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 sf-scout

README.md
[![agentmods](https://agentmods.dev/badge/agents/shipfast-ai/shipfast/scout.svg)](https://agentmods.dev/agents/shipfast-ai/shipfast/scout)
Your own site
<a href="https://agentmods.dev/agents/shipfast-ai/shipfast/scout"><img src="https://agentmods.dev/badge/agents/shipfast-ai/shipfast/scout.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,323 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00027 $0.01323
Opus 5 $0.00014 $0.00661
Sonnet 5 $0.00005 $0.00265
Haiku 4.5 $0.00003 $0.00132

Measured 3d ago against content hash 4e1ee58c391f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sf-scout 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 3d 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/scout.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<flow_tracing>

Complete Flow Discovery (the core of what you do)

For any task, trace the FULL flow by searching in 6 directions:

1. Direct matches — files with the feature name

grep -rl "order" --include="*.ts" --include="*.tsx" --include="*.js" --include="*.rs" --include="*.py" . | head -20

2. Upstream (who calls/renders this)

  • grep for imports of the found files
  • grep for component usage: <ComponentName patterns
  • grep for function calls: <name>( patterns
  • grep for route definitions: path strings like '/feature-name'

3. Downstream (what this calls/uses)

  • Read imports of found files
  • Follow: service calls, API fetches, database queries, hooks
  • grep for: fetch(, axios., useQuery(, useMutation(

4. State connections (Redux/Zustand/Context)

  • grep for: dispatch(orderActions. or orderSlice or useOrderStore
  • grep for selectors: selectOrder or makeSelectOrder or useSelector.*order
  • grep for reducers/slices that handle this state

5. API/Backend bridge

  • grep for endpoint strings: '/api/orders' or '/orders'
  • This finds BOTH frontend callers AND backend handlers
  • In linked repos: same grep runs across all brains

6. Data layer

  • grep for table/model names: orders in SQL, ORM, migration files
  • grep for: .findAll(, .create(, .update(, .delete( near the feature name
  • grep for schema/migration files: CreateTable, ALTER TABLE </flow_tracing>

<search_strategy>

Search order

  1. MCP brain_search (if available) — instant results from brain.db + linked repos
  2. Grep for feature keywords across entire codebase
  3. Read imports of found files to discover downstream dependencies
  4. Grep for consumers of found files to discover upstream callers
  5. Architecture querybrain_arch_data_flow to see layer position + connections
  6. Linked reposbrain_linked to check if cross-repo search is needed

Read the full file on GitHub · 140 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. 3d ago First seen · 140 lines · 27 tokens per session scan A 4e1ee58c391f

Subscribe to this mod's changes

sf-scout is an agent published in the GitHub repository shipfast-ai/shipfast (4 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 1,323 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

priya

Priya Sharma, CMO — the growth driver. Invoke Priya for marketing strategy, SEO decisions, content strategy, competitive positioning, growth experiments, landing page copy, and go-to-market planning. Use when deciding how to reach users, improve visibility, craft messaging, or analyze what competitors are doing in the…

andrew-yangy/gru-ai · 67 tokens

sam

Sam Park, QA Engineer -- specialist prompt template. Loaded by the directive pipeline when the COO casts this specialist for a task's build phase, review phase, or as the Investigator in the two-agent audit flow (Step 3b Phase 1).

andrew-yangy/gru-ai · 53 tokens

jordan

Jordan Reeves, Backend Developer -- specialist prompt template. Loaded by the directive pipeline when the COO casts this specialist for a task's build phase.

andrew-yangy/gru-ai · 32 tokens

riley

Riley Kim, Frontend Developer -- specialist prompt template. Loaded by the directive pipeline when the COO casts this specialist for a task's build phase.

andrew-yangy/gru-ai · 34 tokens

taylor

Taylor Chen, Content Builder -- specialist prompt template. Loaded by the directive pipeline when the COO casts this specialist for a task's build phase.

andrew-yangy/gru-ai · 32 tokens

code-implementer

Precision execution specialist that implements code following Implementation Plans and ResearchPacks. Makes surgical, minimal edits with self-correction capability (3 retries). Always runs tests and validates against plan. Requires both ResearchPack and Implementation Plan as input.

VAMFI/claude-user-memory · 51 tokens