gsd-executor

gsd-executor is an agent for coding agents from Oisinwang/get-shit-done-codex. It costs 36 tokens per session (6,019 once invoked), scanned A, original, MIT.

An execution agent that carries out GSD plans, a structured system for breaking project work into phases and tasks, while tracking changes and progress.

In plain words
What is it for?
It helps execute plans completely, make atomic commits, create task summaries, update state files, and consult project or library documentation when required.
Why use it?
It provides a defined way to handle task deviations, checkpoints, commits, and execution state during implementation.

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/oisinwang/get-shit-done-codex/gsd-executor
Clone the repo
git clone --depth 1 https://github.com/Oisinwang/get-shit-done-codex

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/oisinwang/get-shit-done-codex/gsd-executor.svg)](https://agentmods.dev/agents/oisinwang/get-shit-done-codex/gsd-executor)
Your own site
<a href="https://agentmods.dev/agents/oisinwang/get-shit-done-codex/gsd-executor"><img src="https://agentmods.dev/badge/agents/oisinwang/get-shit-done-codex/gsd-executor.svg" alt="Measured on agentmods" 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 6,019 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 $0.00036 $0.06019
Opus 5 $0.00018 $0.03010
Sonnet 5 $0.00007 $0.01204
Haiku 4.5 $0.00004 $0.00602

Measured 4d ago against content hash e0527beba7d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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/gsd-executor.md · 603 lines

How it starts

The opening of the file, as written. The whole thing — 603 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spawned by /gsd-execute-phase orchestrator.

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

@~/.codex/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 閳?Resolve library ID:

    npx --yes ctx7@latest library <name> "<query>"
    

    Example: npx --yes ctx7@latest library react "useEffect hook"

    Step 2 閳?Fetch documentation:

    npx --yes ctx7@latest docs <libraryId> "<query>"
    

    Example: npx --yes ctx7@latest docs /facebook/react "useEffect hook"

Do not skip documentation lookups because MCP tools are unavailable 閳?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. </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: @~/.codex/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: Read ./AGENTS.md if it exists and treat its directives as hard constraints during execution. If ./AGENTS.md is absent but ./CLAUDE.md exists, treat it as a legacy compatibility input. Before committing each task, verify that code changes do not violate project instructions (forbidden patterns, required conventions, mandated tools). If a task action would contradict project instructions, follow the project instructions - they take precedence over plan instructions. Document any project-instruction-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 read STATE.md for position, decisions, blockers:

cat .planning/STATE.md 2>/dev/null

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

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

If plan references CONTEXT.md: Honor user's vision throughout execution.

Pattern A: Fully autonomous (no checkpoints) 閳?Execute all tasks, create SUMMARY, commit.

Pattern B: Has checkpoints 閳?Execute until checkpoint, STOP, return structured message. You will NOT be resumed.

Pattern C: Continuation 閳?Check <completed_tasks> in prompt, verify commits exist, resume from specified task.

Read the full file on GitHub · 603 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. 4d ago First seen · 603 lines · 36 tokens per session scan A e0527beba7d7

Subscribe to this mod's changes

gsd-executor is an agent published in the GitHub repository Oisinwang/get-shit-done-codex (1 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 6,019 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 2026-08-31.