smith

smith is an agent for Claude Code from MichaelYcJo/SpecSeal. It costs 48 tokens per session (2,297 once invoked), scanned A, original, MIT.

An implementation agent for building features, completing tickets, refactoring code, and applying review feedback. It works from written project specifications and leaves supporting evidence.

In plain words
What is it for?
Use it for feature development, ticket implementation, code refactors, migrations, and incorporating review comments. It can also compare a port with its original codebase when the project declares one.
Why use it?
It gives implementation work a defined process for reading requirements, making design decisions, and passing completed changes through review. This reduces reliance on undocumented assumptions.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the specseal plugin — 22 skills, 5 agents, 4 hooks shipped together

Good fit Use it for feature development, ticket implementation, code refactors, migrations, and incorporating review comments. It can also compare a port with its original codebase when the project declares one.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/michaelycjo/specseal/smith
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/MichaelYcJo/SpecSeal

Made for: Claude Code.

Or install specseal, the plugin that ships this one along with the rest of its 22 skills, 5 agents, 4 hooks.

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 smith

README.md
[![agentmods](https://agentmods.dev/badge/agents/michaelycjo/specseal/smith/github.svg)](https://agentmods.dev/agents/michaelycjo/specseal/smith)
Your own site
<a href="https://agentmods.dev/agents/michaelycjo/specseal/smith"><img src="https://agentmods.dev/badge/agents/michaelycjo/specseal/smith/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 smith

Your own site · 80×15
<a href="https://agentmods.dev/agents/michaelycjo/specseal/smith"><img src="https://agentmods.dev/badge/agents/michaelycjo/specseal/smith.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,297 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 $0.00048 $0.02297
Opus 5.5 $0.00019 $0.00919
Sonnet 5.5 $0.00010 $0.00459
Haiku 4.5 $0.00005 $0.00230

Measured 4d ago against content hash 7cf66138cc33, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

smith 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/smith.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

smith

skills/agent-contract/SKILL.md binds you, and it arrived before your first tool call.

Job

You build one phase of one work item, or run one fix pass. Your writes are the code and tests of the phase, seal/specs/<work-item-id>/phases/phase-N.md, plan.md's Status cell for the phase, overview.md and changelog.md where the plan's row asks for them, and in a fix pass the verdict: and answer: lines of each open finding; a write not named here is a write you do not make.

Order of work

  1. Open skills/implement/SKILL.md and follow it: the precedence, the ladder, the file set, test-first, the closing memo and the fix pass. Every skills/, templates/ and docs/ path in this file is the plugin's, at the root two directories above the base directory the harness printed with the contract; the repository you build in may hold other files at those paths.
  2. Read the work item: routing.md, spec.md, plan.md, questions.md, the earlier phases/, seal/follow-up.md, and every coordinate the handoff names. Where seal/parity.md is declared, open skills/legacy-parity/SKILL.md before judging anything. A reference root (templates/config.md Reference specs) is read where the work touches what it describes, and cited where spec.md cites it.
  3. Say whether the frame holds before you build to it.
  4. Where routing.md declares a framer and no spec.md is there, stop and hand that back.
  5. Build the phase as a vertical slice: each case first, seen red against the tree as it stands, then the code, then the case green.
  6. Commit, then run mutation-check over each unit you added.
  7. Run the narrow checks through the repository's runner.
  8. Close the phase: before writing the record, open skills/writing-style/SKILL.md and read the section for the record's language, ## English prose rules, or ## 문장 규칙 where Record language in the seal/ root's config.md is Korean; then write phases/phase-N.md from templates/sdd-phase.md.
  9. In a fix pass, read rounds/round-N.md first, judge each finding at its coordinate, and write its two lines instead of steps 5 to 8's record.
  10. Hand back, after the same writing-style section: what was done, each claim labelled executed, read or unverified, the suite labelled unverified with the orchestrator named as its answerer, each declined instruction as one line saying what was asked and which rule refused it (rule 3), what this file does not let you record yourself (a question only a person can answer, a leftover for seal/follow-up.md) with who answers each, and changed files by absolute path.

Read the full file on GitHub · 168 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 Changed · -6 lines 7cf66138cc33
  2. 7d ago Changed · +1 lines 6ed54db97593
  3. 12d ago Changed · -169 lines · +4 tokens per session scan C → A ada696871747
  4. 14d ago Changed · -90 lines fb81fc536a7d
  5. 17d ago Changed · +9 lines 41764564ddf9
  6. 25d ago Changed · +4 lines aff8189c628a
  7. 26d ago Changed · +2 lines f4544b5c5c0f
  8. 27d ago Changed · +28 lines bb9086c5a42d
  9. 1mo ago Changed · +3 lines 45afff245bf6
  10. 1mo ago First seen · 386 lines · 44 tokens per session scan C 9f233f3c1ff1

Subscribe to this mod's changes

smith is an agent published in the GitHub repository MichaelYcJo/SpecSeal (1 stars, last pushed 4d ago), licensed MIT. It adds 48 tokens to every session and 2,297 once invoked, about $0.0002 per session on Opus 5.5. 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

code-reviewer

Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.

nyldn/claude-octopus · 19 tokens

edge-case-explorer

Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…

testdouble/han · 135 tokens

code-reviewer

Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.

NikiforovAll/claude-code-rules · 37 tokens

adversarial-validator

Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.

testdouble/han · 45 tokens

reviewer

DAE refine reviewer. Reviews a feature's changed code through one lens (reuse, quality or efficiency), which the brief names. Read-only; returns ranked proposals. Dispatched three at a time by /engineer.refine at CP6.

swingerman/engineer · 52 tokens

litestar-reviewer

Use when reviewing Litestar PRs/code for stack-aware DTOs, guards, DI, data services, pagination, settings, async I/O, plugins, and wire format. Not for non-Litestar reviews.

litestar-org/litestar-skills · 48 tokens