A specification step that turns an agreed design into an ordered implementation checklist. TDD, or test-driven development, means writing tests before the code that makes them pass.

Use it to create setup tasks, implementation cohorts, test-first tasks, and closing work from the earlier specification documents.

It makes the work concrete, shows which tasks can run in parallel, and places test-led work in the intended order.

How lbruton/claude-context configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to lbruton/claude-context. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/lbruton/claude-context/master/.agents/skills/spec-tasks/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/lbruton/claude-context

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/skills/lbruton/claude-context/spec-tasks/github.svg)](https://agentmods.dev/skills/lbruton/claude-context/spec-tasks)

Your own site

<a href="https://agentmods.dev/skills/lbruton/claude-context/spec-tasks"><img src="https://agentmods.dev/badge/skills/lbruton/claude-context/spec-tasks/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/skills/lbruton/claude-context/spec-tasks"><img src="https://agentmods.dev/badge/skills/lbruton/claude-context/spec-tasks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,042 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	$0.00040	$0.01042
Opus 5.5	$0.00016	$0.00417
Sonnet 5.5	$0.00008	$0.00208
Haiku 4.5	$0.00004	$0.00104

Measured 5d ago against content hash 2aff06c729fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

spec-tasks 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 5d 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/skills/spec-tasks/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/spec-tasks ISSUE

Phase 4: turn the approach into a concrete, parallel-aware, TDD-ordered checklist in tasks.md. One artifact, then STOP.

Invocation

/spec-tasks <ISSUE-ID>

Missing <ISSUE-ID> → print Usage: /spec-tasks <ISSUE-ID> and exit.

Read first

.agents/skills/spec/references/conventions.md — folder resolution, phase-boundary discipline, unreconciled-marks pre-check.
The project's .context/spec-conventions.md — worktree/branch convention for Cohort 0, version-lock, and the verbatim closing-task roster.
.agents/skills/spec/references/templates/tasks-template.md — the canonical structure (Cohort 0 setup, A/B/C TDD cohorts, Standard Closing Tasks). Follow it; renumber only.

Steps

Resolve the spec folder; read all three prior phase docs (requirements, discovery, approach).
Unreconciled-marks PRE-CHECK (per conventions.md) on all three. Any unreconciled marks → STOP and name the file + /spec-reconcile {ISSUE-ID} {phase}.
Draft tasks.md from the template:
- Sprint Cohort 0 — Setup: worktree-confirmation task using the project's convention from .context/spec-conventions.md (e.g. StakTrakr → /start-patch, patch/<version> branch). Generic fallback spec/{ISSUE-ID}-{slug} only when no project convention exists.
- TDD cohorts: A = foundation/scaffolding, B = tests (RED — failing tests encoding each EARS acceptance criterion), C = implementation (GREEN). If a task has no testable behavior, B gets a read-only justification task, not a silent skip.
- Mark parallel-safe tasks [P]; give every task explicit File(s):, an Acceptance: line, Maps to: AC-N, and Leverage: hints.
- Standard Closing Tasks: copy from the template, bind skill names to the project roster verbatim (/release patch, codacy-analysis-cli, /vault-update, /pr-resolve, /spec archive). Irrelevant ones → N/A — <reason>, never dropped.
- Set frontmatter approved: empty — the human stamps it.

Read the full file on GitHub · 61 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.

5d ago Changed 2aff06c729fd
9d ago Changed fe8d9a6daaea
11d ago First seen · 61 lines · 40 tokens per session scan A 549cb8919f8e

Subscribe to this mod's changes

spec-tasks is a skill published in the GitHub repository lbruton/claude-context (2 stars, last pushed 5d ago), licensed MIT. It adds 40 tokens to every session and 1,042 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 2026-10-17.

Planning TDD Testing

engram-testing-coverage

TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.

Gentleman-Programming/engram · 25 tokens

conductor-implement

Execute tasks from a track's implementation plan following TDD workflow.

rmyndharis/antigravity-skills · 17 tokens

principle-test-behavior-not-implementation

Apply when you write, change, or keep a test. Assert what the code's users can observe, so that the test fails when that behavior breaks and keeps passing when only the internals change.

michael-denyer/pstack-claude · 50 tokens

mobiai-mobile-tdd

You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.

ArisGuimera/MobiAI-Core · 38 tokens

tdd

This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces the RED-GREEN-REFACTOR cycle with vertical slicing, context isolation between test writing and implementation, human checkpoints, and auto-test feedback loops. Uses multi-agent orchestration with the…

glebis/claude-skills · 92 tokens

iterative-development

TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.

alinaqi/maggy · 24 tokens

claude-context: Skill for Claude Code