What is autospec-implement?

A task runner that carries out the implementation steps recorded in a YAML task file.

Use it to execute all implementation phases or run only one phase from an existing project plan.

It gives the coding agent a defined sequence of work and can limit execution to a chosen phase.

How ariel-frischer/autospec configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ariel-frischer/autospec. 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/ariel-frischer/autospec/main/.agents/skills/autospec-implement/SKILL.md

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ariel-frischer/autospec/autospec-implement/github.svg)](https://agentmods.dev/skills/ariel-frischer/autospec/autospec-implement)

Your own site

<a href="https://agentmods.dev/skills/ariel-frischer/autospec/autospec-implement"><img src="https://agentmods.dev/badge/skills/ariel-frischer/autospec/autospec-implement/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/ariel-frischer/autospec/autospec-implement"><img src="https://agentmods.dev/badge/skills/ariel-frischer/autospec/autospec-implement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,645 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Privilege Escalation · line 141
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
high Privilege Escalation · line 169
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
high Privilege Escalation · line 169
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.

How audits are shown

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	$0.00017	$0.03645
Opus 5	$0.00009	$0.01822
Sonnet 5	$0.00003	$0.00729
Haiku 4.5	$0.00002	$0.00364

Measured 9d ago against content hash a67674ff40fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 9d 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/autospec-implement/SKILL.md · 301 lines

How it starts

The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.

autospec-implement

This Agent Skill is generated from autospec.implement. When the user invokes "$autospec-implement" or "/autospec.implement", load and follow these instructions directly. Treat the text after the skill or command name as "$ARGUMENTS". Do not route back through "autospec implement"; this skill is the prompt for the stage.

Project specs directory: ./specs

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

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 · 301 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.

9d ago First seen · 301 lines · 17 tokens per session scan A a67674ff40fd

Subscribe to this mod's changes

autospec-implement is a skill published in the GitHub repository ariel-frischer/autospec (141 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 3,645 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.

Claude Code command-line developer-tools spec-driven-development speckit

tokf-filter

This skill should be used when the user asks to "create a filter", "write a tokf filter", "add a filter for ", "how do I filter output", or needs guidance on tokf filter step types, templates, pipes, or placement conventions.

mpecan/tokf · 59 tokens

tokf-discover

Find missed token savings by scanning AI coding session files for commands that ran without tokf filtering.

mpecan/tokf · 24 tokens

task-generation

Reference material with the canonical task-format grammar and decomposition rules for plan-to-tasks expansion. Loaded on demand by generate-tasks; not directly invokable.

attilaszasz/sdd-pilot · 35 tokens

implementation-standards

Reference material with coding standards (defensive coding, error handling, testing patterns). Loaded on demand by the Developer sub-agent (.github/agents/developer.md); not directly invokable.

attilaszasz/sdd-pilot · 44 tokens

code-review

You are a senior code reviewer. You receive diffs via stdin.

jrswab/axe · 0 tokens

memorywhale

Query and write durable debugging memory recorded by MemoryWhale. Use when debugging a failure that may have happened before, when you need the exact error/flags/output from an earlier attempt, when the user asks "how did we fix this last time?", or once you've figured out why something failed / how a fix worked and…

wuisabel-gif/MemWhale · 79 tokens

autospec: Skill for Claude Code