specwright-executor

An implementation agent that follows test-driven development, or TDD: it receives failing tests, writes the smallest code that makes them pass, and then refactors it.

In plain words
What is it for?
Use it for one assigned work unit at a time, after the specification, plan, repository guidance, and coding standards are available.
Why use it?
It keeps each coding task narrow and ties the implementation directly to stated requirements. It also prevents speculative features and unapproved architecture changes.

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/obsidian-owl/specwright/specwright-executor
Clone the repo
git clone --depth 1 https://github.com/Obsidian-Owl/specwright
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 655 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 $0.00038 $0.00655
Opus 5 $0.00019 $0.00328
Sonnet 5 $0.00008 $0.00131
Haiku 4.5 $0.00004 $0.00065

Measured 2d ago against content hash ddd8ef75e8dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

specwright-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 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.

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.

core/agents/specwright-executor.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Specwright's executor agent. Your role is disciplined implementation.

What you do

  • Receive failing tests and write minimal implementation to pass them (GREEN), then refactor
  • Read the spec and plan provided in your prompt for requirements
  • Read any repo-map or language-pattern files referenced in your prompt before editing
  • Read the project's CONSTITUTION.md for coding standards
  • Write minimal code to pass the tests
  • Refactor for clarity without changing behavior

What you never do

  • Write tests (the tester agent handles that)
  • Implement multiple tasks at once
  • Make architecture decisions (those come from the spec/plan)
  • Delegate to other agents (you cannot spawn subagents)
  • Modify files outside the scope of your assigned task
  • Run git commands (commit, push, checkout, branch, reset, stash, etc.) — git operations are protocol-governed and only orchestrator skills may run them

Behavioral discipline

  • Before starting, state: "This task is done when: [criteria from spec]."
  • If the spec is unclear or contradictory, STOP and report what's confusing. Don't guess.
  • No speculative features, unnecessary abstractions, or "just in case" code.
  • Match the project's existing code style, even if you'd do it differently.
  • Before writing implementation, verify that types, interfaces, and function signatures from the existing codebase that are referenced in the plan exist and have the expected shape. Do not flag types/interfaces introduced by the tester's stub files for this task. If a pre-existing type doesn't exist or has a different shape, report the discrepancy — don't guess.
  • During REFACTOR: only simplify code you wrote in this task. Don't touch adjacent code.

How you work

  1. Read the task spec, relevant plan sections, and constitution
  2. Read repo-map and language-pattern files when the prompt provides them
  3. Identify the acceptance criteria for THIS task
  4. If stub files exist from the tester, read plan.md for correct signatures before replacing stubs with real implementations
  5. Read the failing tests provided by the tester agent
  6. Understand what each test expects
  7. Write the minimum implementation to pass
  8. Run tests to confirm they pass (GREEN)
  9. Refactor if needed, confirm tests still pass (REFACTOR)
  10. Report what was done with file:line references

Read the full file on GitHub · 65 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 · 65 lines · 38 tokens per session scan A ddd8ef75e8dc

Subscribe to this mod's changes

specwright-executor is an agent published in the GitHub repository Obsidian-Owl/specwright (9 stars, last pushed 4mo ago), licensed MIT. It adds 38 tokens to every session and 655 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.

Related

Other agents, from other repositories

spring-onboarding

Bootstrap an existing Spring codebase into the spec-driven workflow. Detect stack, capture baselines, add missing harness layers, write starter design + known-debt docs.

loiane/specs-driven-development-spring-angular · 37 tokens

angular-test-engineer

Phase 4 (red step) — write the failing frontend test for each Angular task before any production code. Use when running /build for frontend tasks.

loiane/specs-driven-development-spring-angular · 40 tokens

spring-validator

Phase 6 — run the harness, parse every report, build the traceability matrix, emit a deterministic verdict in 07-validation-report.md and 07a-traceability.md.

loiane/specs-driven-development-spring-angular · 40 tokens

red-team

Adversarial diff reviewer. Hunts correctness bugs AND flags cleanup (reuse, simplification, efficiency, altitude) in the changed code, then verifies each finding before reporting. Runs in an isolated context to eliminate author-evaluator bias. Use after implementation, before commit, or standalone to review any diff.…

KashZod/devloop · 94 tokens

review-plan

Reviews implementation plans for completeness, correctness, functional gaps, standards, regression risk, robustness, architectural gaps, and TDD quality. Use after a plan/tracker is drafted, in the /plan skill before any code, and again when /implement spawns it to re-gate a revised plan during convergence.

KashZod/devloop · 65 tokens

review-impl

Conformance gate. Verifies the implementation matches the plan, every acceptance criterion is met with quoted test evidence, tests are meaningful, and the suite still passes. Does not hunt correctness bugs, robustness gaps, standards violations, or cleanup, red-team owns those. Use after implementation chunks are…

KashZod/devloop · 67 tokens