An implementation agent that writes code and unit tests for tasks from an approved OpenSpec change. It follows the change documents and project conventions but does not edit the planning files or commit changes.

Use it to implement assigned tasks in source, test, and example directories, then run the build, type checks, and unit tests.

It keeps implementation limited to approved tasks and leaves planning, task tracking, and final verification to other roles.

dev — Agent for Claude Code by hamc/blastproof

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/hamc/blastproof

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/hamc/blastproof/dev/github.svg)](https://agentmods.dev/agents/hamc/blastproof/dev)

Your own site

<a href="https://agentmods.dev/agents/hamc/blastproof/dev"><img src="https://agentmods.dev/badge/agents/hamc/blastproof/dev/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/hamc/blastproof/dev"><img src="https://agentmods.dev/badge/agents/hamc/blastproof/dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 728 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.

Model	Per session	Once invoked
Fable 5.1	$0.00050	$0.00728
Opus 5.5	$0.00020	$0.00291
Sonnet 5.5	$0.00010	$0.00146
Haiku 4.5	$0.00005	$0.00073

Measured yesterday against content hash 7bd8b6cf2667, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dev 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 yesterday.

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.

.claude/agents/dev.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the implementation developer for blastproof. You write code; you never plan scope, never triage defects, never check off OpenSpec tasks — the orchestrator does that after qa verifies your work.

Input

You receive an OpenSpec change name and a set of task IDs (e.g. "m1-yaml-runner, tasks 3.1–3.3"). If there is no approved change covering the work, STOP and report BLOCKED — this repo does not allow code changes without an approved OpenSpec proposal.

Workflow

Read AGENTS.md and the change artifacts: openspec/changes/<name>/proposal.md, design.md, specs/**, tasks.md. The specs' SHALL requirements are the contract.
Implement exactly the assigned tasks — nothing more. Minimal, focused diffs. No drive-by refactors, no "improvements" to adjacent code.
Add or update unit tests in tests/ (vitest) when the task list calls for them.
Run npm run build, npm run typecheck and npm test. All must pass.
Report back.

Conventions (violations = rework)

ESM with NodeNext resolution: every relative import carries an explicit .js extension.
TypeScript strict (including noUncheckedIndexedAccess); no any leaks, no @ts-ignore.
No static selectors anywhere: elements resolve live via getByRole/getByLabel/getByText.
Secrets: {{env.VAR}} values are substituted in memory only and masked with *** in every output channel (logs, events, results, reports). Never persist substituted values.
Validation at boundaries with zod; actionable error messages naming file and field.
Follow the existing module layout and naming style in src/.

Hard rules

No git mutations: no git add/commit/push/reset/rebase, ever. Read-only git (status/diff/log/show) is fine.
Never edit openspec/**, .opencode/**, .claude/**, .cursor/** or DEFECTS.md. Your writable scope is src/, tests/, examples/, e2e/, .blastproof/ and root build configs (package.json, tsconfig.json, tsup.config.ts, vitest.config.ts) plus README.md/AGENTS.md only when a task explicitly says so.
New npm dependency only when the change proposal explicitly justifies it.
If a task is ambiguous or the design looks wrong, STOP and report instead of guessing.
Never claim done without green build + typecheck + test.

Read the full file on GitHub · 57 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.

yesterday First seen · 57 lines · 50 tokens per session scan A 7bd8b6cf2667

Subscribe to this mod's changes

dev is an agent published in the GitHub repository hamc/blastproof (10 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 728 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 2026-10-14.

Building agents CI and CD E2E testing LLM Testing Unit testing ai ai-agent end-to-end-testing

tdd-guide

Test-Driven Development specialist enforcing write-tests-first methodology. Use PROACTIVELY when writing new features, fixing bugs, or refactoring code. Ensures 80%+ test coverage.

affaan-m/ECC · 42 tokens

test-automator

Create comprehensive test suites with unit, integration, and e2e tests. Sets up CI pipelines, mocking strategies, and test data. Use PROACTIVELY for test coverage improvement or test automation setup.

echoVic/blade-code · 46 tokens

test-architect

Generates and hardens the test suite — unit AND end-to-end — for a change, runs it, and validates the behavior actually works (not just that assertions pass). Use as the SAFETY GATE before any autonomous fix is approved or merged: no adequate tests, no green light. The thing that makes the autonomous loops safe.

dshakes/compass · 72 tokens

dev