autospec.implement

autospec.implement is a command for Claude Code from ariel-frischer/autospec. It costs 12 tokens per session (3,560 once invoked), scanned A, original, MIT.

A command for carrying out software tasks listed in a tasks.yaml file. It can run every phase or only a specified phase of an implementation plan.

In plain words
What is it for?
Use it to process an implementation plan, run one selected phase, or use a supplied context file containing the relevant project artifacts.
Why use it?
It removes the need to execute planned implementation tasks manually and helps keep work within defined phase boundaries.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

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 commands/ariel-frischer/autospec/autospec.implement
Clone the repo
git clone --depth 1 https://github.com/ariel-frischer/autospec

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.

agentmods badge for autospec.implement

README.md
[![agentmods](https://agentmods.dev/badge/commands/ariel-frischer/autospec/autospec.implement.svg)](https://agentmods.dev/commands/ariel-frischer/autospec/autospec.implement)
Your own site
<a href="https://agentmods.dev/commands/ariel-frischer/autospec/autospec.implement"><img src="https://agentmods.dev/badge/commands/ariel-frischer/autospec/autospec.implement.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,560 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 5.1 $0.00012 $0.03560
Opus 5 $0.00006 $0.01780
Sonnet 5 $0.00002 $0.00712
Haiku 4.5 $0.00001 $0.00356

Measured 6d ago against content hash 8ae2ee55d30d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

autospec.implement 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 6d 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.

internal/cli/admin/.claude/commands/autospec.implement.md · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Input

$ARGUMENTS

You MUST consider the user input before proceeding (if not empty).

Execution Boundaries (CRITICAL)

Flag Behavior
--phase N Execute ONLY phase N tasks. After completion, output "Phase N complete." and TERMINATE. Do NOT proceed to other phases.
--context-file Use bundled artifacts from context file. Do NOT separately read files listed in _context_meta.skip_reads.
(no flags) Execute all phases sequentially.

Pre-computed Context

The following paths have been pre-computed and are available for use:

  • FEATURE_DIR: {{.FeatureDir}}
  • TASKS_FILE: {{.TasksFile}}
  • CONSTITUTION_FILE: {{if .ConstitutionFile}}{{.ConstitutionFile}}{{else}}not found{{end}}
  • IS_GIT_REPO: {{.IsGitRepo}}

Outline

  1. Phase Context Metadata (CRITICAL - Token Optimization):

    Check if --context-file was used. If so, parse the _context_meta section FIRST before any other file reads.

    _context_meta Fields:

    • phase_artifacts_bundled: true - Indicates that spec.yaml, plan.yaml, and tasks.yaml (phase-filtered) are already bundled in this context file
    • bundled_artifacts - Lists the artifacts included, such as ["spec.yaml", "plan.yaml", "tasks.yaml (phase-filtered)", "constitution.yaml"]
    • has_governance - Boolean indicating whether project governance is bundled in the governance: section
      • If true: Use the bundled governance: data as the constitution/governance source of truth
      • If false: No constitution was bundled; do not search for a governance file during context-file execution
    • governance_file - Path to the constitution file when governance is bundled
    • has_checklists - Boolean indicating whether a checklists/ directory exists for this feature
      • If false: DO NOT check for, scan, or read from the checklists directory - it doesn't exist, skip step 3 entirely
      • If true: Checklists directory exists, proceed to step 3
    • skip_reads - Explicit list of file paths that are already bundled and MUST NOT be read separately

Read the full file on GitHub · 292 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. 6d ago First seen · 292 lines · 12 tokens per session scan A 8ae2ee55d30d

Subscribe to this mod's changes

autospec.implement is a command published in the GitHub repository ariel-frischer/autospec (141 stars, last pushed 27d ago), licensed MIT. It adds 12 tokens to every session and 3,560 once invoked, about $0.0001 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 2026-08-30.