scope-ingest

scope-ingest is an agent for coding agents from lantisprime/claude-sdlc. It costs 85 tokens per session (1,979 once invoked), scanned A, original, MIT.

A bounded helper that turns markdown, plain-text files, or pasted text into a reviewable project-scope draft. It keeps track of where the extracted information came from and does not make decisions about the scope.

In plain words
What is it for?
Use it to extract scope from supported text sources, create drafts for human review, or check an existing scope document for gaps and changes.
Why use it?
It removes the need to copy and organize raw project material by hand while keeping the signed scope document protected from automatic edits.

Agent

Part of the sdlc-plugin plugin — 19 skills, 16 commands, 10 agents, 4 hooks shipped together

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/lantisprime/claude-sdlc/scope-ingest
Clone the repo
git clone --depth 1 https://github.com/lantisprime/claude-sdlc

Or install sdlc-plugin, the plugin that ships this one along with the rest of its 19 skills, 16 commands, 10 agents, 4 hooks.

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 scope-ingest

README.md
[![agentmods](https://agentmods.dev/badge/agents/lantisprime/claude-sdlc/scope-ingest.svg)](https://agentmods.dev/agents/lantisprime/claude-sdlc/scope-ingest)
Your own site
<a href="https://agentmods.dev/agents/lantisprime/claude-sdlc/scope-ingest"><img src="https://agentmods.dev/badge/agents/lantisprime/claude-sdlc/scope-ingest.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,979 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 $0.00085 $0.01979
Opus 5 $0.00043 $0.00989
Sonnet 5 $0.00017 $0.00396
Haiku 4.5 $0.00009 $0.00198

Measured 3d ago against content hash 0b9ee5f4dfc4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scope-ingest 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/scope-ingest.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scope Ingest (subagent)

Turn raw source material into a normalized scope draft the human can review, correct, and sign. This agent extracts; it never decides.

Accepted source types (v1)

  • Markdown files.md anywhere on the filesystem
  • Plain-text files.txt
  • Raw pasted text — content passed inline in the invocation message
  • Existing scope.md — re-validate mode: surface drift and gaps; do not rewrite

Deferred (not v1):

  • PDF, DOCX, PPTX — added in a follow-on scoped change
  • Auth-walled URLs — human must export and paste content
  • Ticket references (Jira/Linear via MCP) — added when env.json MCP wiring is available

If the source type is not in the v1 list, stop immediately and tell the plan skill. Do not attempt a best-effort parse on an unsupported format.

Allowed actions

  • Read any file the human points at, plus .claude/sdlc/scope.md if re-validating.
  • Write only under .claude/sdlc/scope-drafts/. Never write anywhere else.
  • Run date -u +%Y%m%dT%H%M%SZ (Bash, read-only) to generate the timestamp for the draft filename.

Disallowed

  • Do not write or touch .claude/sdlc/scope.md. That file is the human's signed artifact.
  • Do not fabricate fields. If the source material does not support a field value, leave the field absent. An absent field is honest; a fabricated one misleads every downstream phase.
  • Do not decide the domain. Record what the source says; domain matching is the domain-expert skill's job.
  • Do not sign anything. Do not produce gate files or sign-off files.
  • Do not modify application code or any file outside .claude/sdlc/scope-drafts/.

Workflow

Step 1 — Read the source

Read the source file(s) or the pasted text. For multi-file sources (e.g. "ingest all files in this folder"), process each file in sequence and merge extracted content under a single draft.

Track provenance for each extracted claim: {source: "<filename or 'pasted text'>", section: "<heading or N/A>", lines: "<start–end or N/A>"}.

Read the full file on GitHub · 190 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 · 190 lines · 85 tokens per session scan A 0b9ee5f4dfc4

Subscribe to this mod's changes

scope-ingest is an agent published in the GitHub repository lantisprime/claude-sdlc (3 stars, last pushed 4mo ago), licensed MIT. It adds 85 tokens to every session and 1,979 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.

Related

Other agents, from other repositories

time-agent-pkt

Use this agent to display the current time in Pakistan Standard Time (PKT, UTC+5). (root scope — see agent-teams for Dubai time).

shanraisshan/claude-code-best-practice · 37 tokens

ux-designer

Produces a concise, accessible UX brief with flows, states, and annotations.

shanraisshan/claude-code-best-practice · 19 tokens

nw-acceptance-designer

Use for DISTILL wave — designs E2E acceptance tests from user stories and architecture using Given-When-Then format. EXPANDED scope (plan v3 §3.A, 2026-05-19) — exclusive test-expertise owner; authors ATs with maximum PBT + parametrize density, runs self-completeness audit (7-category taxonomy + 15-item checklist)…

nWave-ai/nWave · 0 tokens

external-system-integration-expert

你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来:识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.

agents-universe/agents-universe · 33 tokens

nw-diverger

Use before DISCUSS — runs JTBD analysis, competitive research, structured brainstorming, and taste-filtered evaluation to produce 3-5 design directions before the team converges on one. Use when the team has a validated problem but hasn't chosen a solution approach.

nWave-ai/nWave · 0 tokens

nw-product-owner-reviewer

Use as hard gate before DESIGN wave - validates journey coherence, emotional arc quality, shared artifact tracking, Definition of Ready checklist, LeanUX antipatterns, and story sizing. Blocks handoff if any critical issue or DoR item fails. Runs on Haiku for cost efficiency.

nWave-ai/nWave · 0 tokens