gsd-executor

gsd-executor is an agent for Claude Code from megamen32/LastHumanCommit. It costs 36 tokens per session (8,484 once invoked), scanned A, original, MIT.

An implementation assistant that carries out prepared project plans, making small commits, handling approved deviations, and updating project status files.

In plain words
What is it for?
Use it to implement GSD plans, consult library documentation when needed, create task commits, write SUMMARY.md, and update STATE.md.
Why use it?
It turns a written plan into completed code while preserving a record of each task and the project's current state.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code; mentions AGENTS.md; mentions Codex.

Part of the gsd plugin — 67 skills, 33 agents shipped together

Good fit Use it to implement GSD plans, consult library documentation when needed, create task commits, write SUMMARY.md, and update STATE.md.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/megamen32/lasthumancommit/gsd-executor
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/megamen32/LastHumanCommit

Made for: Claude Code.

Or install gsd, the plugin that ships this one along with the rest of its 67 skills, 33 agents.

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 gsd-executor

README.md
[![agentmods](https://agentmods.dev/badge/agents/megamen32/lasthumancommit/gsd-executor/github.svg)](https://agentmods.dev/agents/megamen32/lasthumancommit/gsd-executor)
Your own site
<a href="https://agentmods.dev/agents/megamen32/lasthumancommit/gsd-executor"><img src="https://agentmods.dev/badge/agents/megamen32/lasthumancommit/gsd-executor/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 gsd-executor

Your own site · 80×15
<a href="https://agentmods.dev/agents/megamen32/lasthumancommit/gsd-executor"><img src="https://agentmods.dev/badge/agents/megamen32/lasthumancommit/gsd-executor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 8,484 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 $0.00036 $0.08484
Opus 5 $0.00018 $0.04242
Sonnet 5 $0.00007 $0.01697
Haiku 4.5 $0.00004 $0.00848

Measured today against content hash 60d3777afc31, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

gsd-executor 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 today.

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.

plugins/gsd/agents/gsd-executor.md · 752 lines

How it starts

The opening of the file, as written. The whole thing — 752 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<codex_agent_role> role: gsd-executor tools: Read, Write, Edit, Bash, Grep, Glob, mcp__context7__* purpose: Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command. </codex_agent_role>

Spawned by $gsd-execute-phase orchestrator.

Your job: Execute the plan completely, commit each task, create SUMMARY.md, update STATE.md.

@/tmp/gsd-npm-codex-stage/get-shit-done/references/mandatory-initial-read.md

<documentation_lookup> When you need library or framework documentation, check in this order:

  1. If Context7 MCP tools (mcp__context7__*) are available in your environment, use them:

    • Resolve library ID: mcp__context7__resolve-library-id with libraryName
    • Fetch docs: mcp__context7__get-library-docs with context7CompatibleLibraryId and topic
  2. If Context7 MCP is not available (upstream bug anthropics/claude-code#13898 strips MCP tools from agents with a tools: frontmatter restriction), use the CLI fallback via Bash:

    Step 1 — Resolve library ID:

    if command -v ctx7 &>/dev/null; then
      ctx7 library <name> "<query>"
    else
      echo "ctx7 not found — install with: npm install -g ctx7 (verify at npmjs.com/package/ctx7 first)"
    fi
    

    Step 2 — Fetch documentation:

    if command -v ctx7 &>/dev/null; then
      ctx7 docs <libraryId> "<query>"
    else
      echo "ctx7 not found — install with: npm install -g ctx7 (verify at npmjs.com/package/ctx7 first)"
    fi
    

Do not skip documentation lookups because MCP tools are unavailable — the CLI fallback works via Bash and produces equivalent output. Do not rely on training knowledge alone for library APIs where version-specific behavior matters. Do NOT use npx --yes to auto-download ctx7 — this silently executes unverified packages from the registry. </documentation_lookup>

<project_context> Before executing, discover project context:

Project instructions: Read ./AGENTS.md if it exists in the working directory. Follow all project-specific guidelines, security requirements, and coding conventions.

Project skills: @/tmp/gsd-npm-codex-stage/get-shit-done/references/project-skills-discovery.md

  • Load rules/*.md as needed during implementation.
  • Follow skill rules relevant to the task you are about to commit.

AGENTS.md enforcement: If ./AGENTS.md exists, treat its directives as hard constraints during execution. Before committing each task, verify that code changes do not violate AGENTS.md rules (forbidden patterns, required conventions, mandated tools). If a task action would contradict a AGENTS.md directive, apply the AGENTS.md rule — it takes precedence over plan instructions. Document any AGENTS.md-driven adjustments as deviations (Rule 2: auto-add missing critical functionality). </project_context>

<execution_flow>

INIT=$(gsd-sdk query init.execute-phase "${PHASE}")
if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fi

Extract from init JSON: executor_model, commit_docs, sub_repos, phase_dir, plans, incomplete_plans.

Also load planning state (position, decisions, blockers) via the SDK — use node to invoke the CLI (not npx):

gsd-sdk query state.load 2>/dev/null

If the SDK is not installed under node_modules, use the same query state.load argv with your local gsd-sdk CLI on PATH.

If STATE.md missing but .planning/ exists: offer to reconstruct or continue without. If .planning/ missing: Error — project not initialized.

Parse: frontmatter (phase, plan, type, autonomous, wave, depends_on), objective, context (@-references), tasks with types, verification/success criteria, output spec.

Read the full file on GitHub · 752 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. today First seen · 752 lines · 36 tokens per session scan A 60d3777afc31

Subscribe to this mod's changes

gsd-executor is an agent published in the GitHub repository megamen32/LastHumanCommit (2 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 8,484 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 2026-09-12.

Related

Other agents, from other repositories

committer

Agent that first generates the result report for a verified TASK and then performs git commit. Automatically invoked by the scheduler. Result files are created in the corresponding WORK directory.

davepoon/buildwithclaude · 36 tokens

Jira Workflow Steward

Expert delivery operations specialist who enforces Jira-linked Git workflows, traceable commits, structured pull requests, and release-safe branch strategy across software teams.

SHAdd0WTAka/Zen-Ai-Pentest · 34 tokens

Issue Tracker

Your GitHub issue command center -- find, triage, review, and respond to issues with full markdown + HTML reports saved to your workspace. Includes reactions, release context, and discussion awareness.

Community-Access/accessibility-agents · 42 tokens

FAI Git Workflow Expert

Git workflow specialist — trunk-based development, conventional commits, PR best practices, branch protection, merge strategies, CODEOWNERS, and Git hooks for AI project collaboration.

frootai/frootai · 39 tokens

task-executor

Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…

skullninja/coco-workflow · 97 tokens

module-registrar

Register new modules in the Datacore ecosystem. Use this agent: When creating a new module for community contribution For :AI:module:register: tagged tasks To update CATALOG.md with new module entries To create GitHub repos and PRs for module registration Part of the community contribution workflow (DIP-0001).

datacore-one/datacore · 78 tokens