Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/griffinwork40-gather
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/gather
What's inside
- Skill name
gather- Description
- Parallel context-gathering for a code area. Use when you need to understand a module, feature, or subsystem and would otherwise read 3+ files sequentially — dispatches two agents in parallel to map structure and test coverage in one wave.
- License
- Apache-2.0
- Instructions
- 39 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
## Dispatch protocol You MUST emit **exactly two** `agent` tool_use blocks in a **single response turn** — both calls in the same assistant message, before either result arrives. Do not dispatch the second agent in a later turn after seeing the first agent's reply. Do not dispatch three agents. Do not dispatch one. Correct shape of your next response: ``` <assistant turn> <tool_use name="agent" id="…"> Structure Agent prompt </tool_use> <tool_use name="agent" id="…"> Test Agent prompt </tool_use> </assistant turn> ``` If you find yourself about to send a single `agent` call and wait, stop — that is the failure mode this skill exists to prevent. ## The two agents When understanding a task requires reading multiple related files (imports, callers, tests, configs, types), dispatch these two — concurrently, per the protocol above: 1. **Structure Agent** (Explore, thoroughness matched to scope) — Find and read the target file(s), all direct imports, callers, and config references. Return: - `files_read`: absolute paths examined - `call_graph`: how components connect (one paragraph) - `public_interfaces`: function signatures, types, or contracts that govern the area - `entry_points`: where control flow enters 2. **Test Agent** (Explore, "medium") — Find test files that exercise the target area, read them, identify what paths are covered and what's missing. Return: - `test_files`: absolute paths of relevant tests - `coverage_summary`: what behaviors/branches tests exercise - `untested_paths`: code paths with no test coverage When both return, merge into a unified context map. If either agent's output has gaps (e.g., Structure Agent missed config, Test Agent found no tests), issue one targeted follow-up Read — do not re-dispatch. ### When NOT to use - You already know exactly which 1–2 files to read — just read them directly. - The task is a simple grep or symbol lookup — use Grep or Glob. - You're mid-edit and need to check one adjacent file — a single Read is fine.
From griffinwork40/agent-framework, Apache-2.0.
More from griffinwork40/agent-framework
- 0.646score
shadow-verify
griffinwork40
Dispatch a parallel adversarial verifier wave after any high-stakes sub-agent investigation (code reviews, audits, findings reports, large refactors, gap…
SkillAFreshness: A★ 23Claude Code +9 - 0.646score
ship
griffinwork40
Release pipeline for already-done local work.
SkillAFreshness: A★ 23Claude Code +9 - 0.646score
review
griffinwork40
Dispatches parallel dimension agents across a diff, PR (URL or number), commit SHA, branch, staged changes, or patch file — covering security, correctness…
SkillAFreshness: A★ 23Claude Code +9 - 0.646score
simplify
griffinwork40
Discovers incidental complexity, duplication, and dead code in a codebase and produces a ranked, behavior-preserving reduction plan — optionally applying safe…
SkillAFreshness: A★ 23Claude Code +9 - 0.646score
ground-state
griffinwork40
Before starting any non-trivial implementation, run a pre-flight reconnaissance pass to triangulate git state, project infrastructure, and prior-session memory.
SkillAFreshness: A★ 23Claude Code +9 - 0.646score
fix-pr
griffinwork40
One-verb pipeline for the operator's highest-frequency manual loop: fetch a PR's unresolved reviewer feedback (inline review comments, review-summary bodies…
SkillAFreshness: A★ 23Claude Code +9 - 0.646score
refactor
griffinwork40
Orchestrates safe, large-scale structural changes across a codebase — symbol renames, API migrations, pattern standardizations, layer restructurings.
SkillAFreshness: A★ 23Claude Code +9 - 0.645score
forge-friction
griffinwork40
Surface recurring friction from session telemetry and generate targeted skills.
SkillAFreshness: A★ 23Claude Code +9 - 0.641score
diagnose
griffinwork40
Parallel root-cause analysis for bugs and failing tests.
SkillAFreshness: A★ 23Claude Code +9 - 0.641score
automate
griffinwork40
Set up a scheduled headless Claude run that sends summaries to Telegram.
SkillAFreshness: A★ 23Claude Code +9 - 0.640score
research
griffinwork40
Dispatches two sub-agents in parallel to gather external and local context for the current task.
SkillAFreshness: A★ 23Claude Code +9 - 0.606score
resolve
griffinwork40
Resolves PR code review feedback.
SkillBFreshness: B★ 23Claude Code +9
Signals
- Stars
- 23
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 18, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/griffinwork40/agent-framework
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from griffinwork40
- 0.646score
ship
griffinwork40
Release pipeline for already-done local work.
SkillAFreshness: A★ 23Claude Code +9 - 0.646score
simplify
griffinwork40
Discovers incidental complexity, duplication, and dead code in a codebase and produces a ranked, behavior-preserving reduction plan — optionally applying safe…
SkillAFreshness: A★ 23Claude Code +9 - 0.646score
shadow-verify
griffinwork40
Dispatch a parallel adversarial verifier wave after any high-stakes sub-agent investigation (code reviews, audits, findings reports, large refactors, gap…
SkillAFreshness: A★ 23Claude Code +9 - 0.646score
ground-state
griffinwork40
Before starting any non-trivial implementation, run a pre-flight reconnaissance pass to triangulate git state, project infrastructure, and prior-session memory.
SkillAFreshness: A★ 23Claude Code +9 - 0.646score
refactor
griffinwork40
Orchestrates safe, large-scale structural changes across a codebase — symbol renames, API migrations, pattern standardizations, layer restructurings.
SkillAFreshness: A★ 23Claude Code +9 - 0.646score
fix-pr
griffinwork40
One-verb pipeline for the operator's highest-frequency manual loop: fetch a PR's unresolved reviewer feedback (inline review comments, review-summary bodies…
SkillAFreshness: A★ 23Claude Code +9
Cite this page
gather skill. Agent Mart. https://agentmart.dev/skills/griffinwork40-gather (last updated 2026-10-24)