ContextGatherer

ContextGatherer is an agent for Claude Code from attilaszasz/sdd-pilot. It costs 30 tokens per session (2,778 once invoked), scanned A, original, MIT.

A helper agent for SDD Pilot that gathers the current feature branch, its project directory, required files, and shared documents. A feature branch is a separate line of code changes used to develop one feature.

In plain words
What is it for?
Use it at the start of SDD Pilot workflows to resolve repository state and return structured context for specification, planning, task, implementation, clarification, checklist, or analysis work.
Why use it?
It gives other development agents the project context they need before planning or changing code. This reduces confusion about which branch, files, and prerequisites are in scope.

Agent for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions subagents; Copilot chat-mode frontmatter (tools: vscode/*).

Good fit Use it at the start of SDD Pilot workflows to resolve repository state and return structured context for specification, planning, task, implementation, clarification, checklist, or analysis work.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/attilaszasz/sdd-pilot/_context-gatherer
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.

Clone the repo
git clone --depth 1 https://github.com/attilaszasz/sdd-pilot

Made for: Claude Code.

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 ContextGatherer

README.md
[![agentmods](https://agentmods.dev/badge/agents/attilaszasz/sdd-pilot/_context-gatherer/github.svg)](https://agentmods.dev/agents/attilaszasz/sdd-pilot/_context-gatherer)
Your own site
<a href="https://agentmods.dev/agents/attilaszasz/sdd-pilot/_context-gatherer"><img src="https://agentmods.dev/badge/agents/attilaszasz/sdd-pilot/_context-gatherer/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.

agentmods 80×15 button for ContextGatherer

Your own site · 80×15
<a href="https://agentmods.dev/agents/attilaszasz/sdd-pilot/_context-gatherer"><img src="https://agentmods.dev/badge/agents/attilaszasz/sdd-pilot/_context-gatherer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,778 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00030 $0.02778
Opus 5 $0.00015 $0.01389
Sonnet 5 $0.00006 $0.00556
Haiku 4.5 $0.00003 $0.00278

Measured 9d ago against content hash 926ce44f4a49, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ContextGatherer 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 9d 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.

.github/agents/_context-gatherer.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task

Resolve branch, feature directory, prerequisite artifacts, and shared document references.

Inputs

Repository state, filesystem listings, git metadata, and config documents.

Execution Rules

Run autonomously, avoid user-facing prose, and emit normalized structured keys.

Output Format

Return a deterministic context report consumed by parent agents.

You are the SDD Pilot Context Gatherer sub-agent. You run autonomously and return a structured context report. You never interact with the user directly.

0. Runtime Mode

Set AUTOPILOT only from the explicit autopilot input: exactly trueAUTOPILOT=true; omitted, false, or any other value → AUTOPILOT=false. Never derive runtime mode from .github/sddp-config.md; ## Autopilot**Enabled**: is permission checked by /sddp-autopilot, not an ambient mode switch.

Mode Selection

  • Full mode (default — /sddp-specify): Execute all steps 1–6.
  • Quick mode (/sddp-plan, /sddp-tasks, /sddp-implement, /sddp-clarify, /sddp-checklist, /sddp-analyze): Before any read, marker check, creation, or write, run node scripts/resolve-feature-dir.mjs "FEATURE_DIR" from the repository root. Accept only its normalized specs/<feature> result. On failure set CONTEXT_BLOCKED=true, BLOCKING_REASON to the resolver error, FEATURE_DIR="", and DIR_EXISTS=false; otherwise skip Steps 1–2, set BRANCH="", HAS_GIT=false, VALID_BRANCH=false, REPO_STATE="quick-mode", and begin at Step 3.

1. Detect Branch

Read the full file on GitHub · 134 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. 9d ago First seen · 134 lines · 30 tokens per session scan A 926ce44f4a49

Subscribe to this mod's changes

ContextGatherer is an agent published in the GitHub repository attilaszasz/sdd-pilot (95 stars, last pushed 4d ago), licensed MIT. It adds 30 tokens to every session and 2,778 once invoked, about $0.0002 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 2026-08-30.

Related

Other agents, from other repositories

Spec-Driven

Use this planner when the user wants implementation to be specified and approved before code changes. Select the brief lane by default for bounded work or the full requirements -> design -> tasks lifecycle for high-risk work. Never implement before the selected lane's approval gate.

lindoelio/spec-driven-steroids · 54 tokens

sharp-edges-analyzer

Evaluates APIs, configurations, and library interfaces for misuse resistance and footgun potential. Use when reviewing code for error-prone designs, dangerous defaults, or APIs that make security mistakes easy.

stefaniuk/loadout · 44 tokens

sdd-scout

Architecture scout used only by /sdd-architecture-scan. Analyzes one worklist unit and writes its report to .sdd-scan/reports/. Not for general tasks.

GregorBiswanger/featherspec · 43 tokens

angular-implementer

Phase 4 (green/refactor/simplify) — minimum Angular production code to pass the failing test, then refactor without behavior change, then apply clarity-over-cleverness.

loiane/specs-driven-development-spring-angular · 42 tokens

angular-architect

Phase 3 — design the Angular feature, decompose into TDD-shaped frontend tasks, write ADRs. Use when the user asks for design, plan, or runs /plan for a feature touching the Angular UI.

loiane/specs-driven-development-spring-angular · 48 tokens

ndv-signal

Metrics skeptic. Use when reviewing engineering KPIs, OKRs, sprint velocity, test coverage targets, DORA metrics, or any measurement system. Audits whether metrics measure what they claim to measure. Goodhart's Law as a cognitive style — the moment a measure becomes a target, it stops being a measure, and Signal…

emb715/neurodiveragents · 76 tokens