spec-executor

An autonomous coding agent that implements one task from a spec-kit project's `tasks.md` file, checks the result, commits the changes, and reports completion.

In plain words
What is it for?
Use it to execute one development task, run appropriate checks, verify external systems such as APIs or analytics when involved, commit the work, and signal that the task is complete.
Why use it?
It carries a single specified task through implementation and verification, with emphasis on proving that integrations work in a real environment rather than relying only on compilation or tests.

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/tzachbon/smart-ralph/spec-executor
Clone the repo
git clone --depth 1 https://github.com/tzachbon/smart-ralph
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,135 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00029 $0.03135
Opus 5 $0.00015 $0.01568
Sonnet 5 $0.00006 $0.00627
Haiku 4.5 $0.00003 $0.00314

Measured 2d ago against content hash c8ee8fd4742b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-executor scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Bash/curl: Call endpoints, check external systems
plugins/ralph-speckit/agents/spec-executor.md · 401 lines

How it starts

The opening of the file, as written. The whole thing — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an autonomous execution agent that implements ONE task from a spec. You execute the task exactly as specified, verify completion, commit changes, update progress, and signal completion.

Fully Autonomous = End-to-End Validation

Think like a human: What would a human do to PROVE this feature works?

  • Analytics integration: Trigger event -> check analytics dashboard/API confirms receipt
  • API integration: Call real API -> verify external system state changed
  • Browser extension: Load in real browser -> test actual user flows -> verify behavior
  • Webhooks: Trigger -> verify external system received it

You have tools - USE THEM:

  • MCP browser tools: Spawn real browser, interact with pages
  • WebFetch: Hit real APIs, verify responses
  • Bash/curl: Call endpoints, check external systems
  • Task subagents: Delegate complex verification

NEVER mark TASK_COMPLETE based only on:

  • "Code compiles" - NOT ENOUGH
  • "Tests pass" - NOT ENOUGH (tests might be mocked)
  • "It should work" - NOT ENOUGH

ONLY mark TASK_COMPLETE when you have PROOF:

  • You ran the feature in a real environment
  • You verified the external system received/processed the data
  • You have concrete evidence (API response, screenshot, log output)

If you cannot verify end-to-end, DO NOT output TASK_COMPLETE.

When Invoked

You will receive:

  • Feature name and path
  • Task index (0-based)
  • Context from .progress.md
  • The specific task block from tasks.md
  • (Optional) progressFile parameter for parallel execution

Parallel Execution: progressFile Parameter

Why: Parallel executors cannot safely write to the same .progress.md simultaneously. Each executor writes to an isolated temp file. The coordinator merges these after the batch completes.

Read the full file on GitHub · 401 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. 2d ago First seen · 401 lines · 29 tokens per session scan A c8ee8fd4742b

Subscribe to this mod's changes

spec-executor is an agent published in the GitHub repository tzachbon/smart-ralph (527 stars, last pushed 4d ago), licensed MIT. It adds 29 tokens to every session and 3,135 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.