A reference for the SpecLeft command-line workflow, a tool for managing feature specifications and their tests. It covers validation, progress checks, coverage, and safe command use.

Use it to validate or list features, add specifications, check coverage and status, verify skills, and run the project tests.

It provides repeatable checks and explains how to avoid overwriting files or misreading command results.

docs — Skill for Claude Code and Codex by SpecLeft/specleft

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.

Any agent

npx skills add SpecLeft/specleft --skill docs

Clone the repo

git clone --depth 1 https://github.com/SpecLeft/specleft

Made for: Claude Code, Codex.

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/specleft/specleft/docs/github.svg)](https://agentmods.dev/skills/specleft/specleft/docs)

Your own site

<a href="https://agentmods.dev/skills/specleft/specleft/docs"><img src="https://agentmods.dev/badge/skills/specleft/specleft/docs/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/specleft/specleft/docs"><img src="https://agentmods.dev/badge/skills/specleft/specleft/docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 980 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	$0.00000	$0.00980
Opus 5.5	$0.00000	$0.00392
Sonnet 5.5	$0.00000	$0.00196
Haiku 4.5	$0.00000	$0.00098

Measured 1mo ago against content hash da7b607179f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

docs 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 1mo 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.

docs/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SpecLeft CLI Reference

Setup

export SPECLEFT_COMPACT=1 All commands below run in compact mode.

Workflow

specleft next --limit 1
Implement test logic
specleft features validate
specleft skill verify
pytest
Repeat

Quick checks

Validation: check exit code first, parse JSON only on failure
Coverage: specleft coverage --threshold 100 and check exit code
Status: specleft status for progress snapshots

Safety

Always --dry-run before writing files
Never use --force unless explicitly requested
Exit codes: 0 = success, 1 = error, 2 = cancelled
Commands are deterministic and safe to retry

Features

Validate specs

specleft features validate --format json [--dir PATH] [--strict] Validate before generating tests. --strict treats warnings as errors.

List features

specleft features list --format json [--dir PATH]

Show stats

specleft features stats --format json [--dir PATH] [--tests-dir PATH]

Add a feature

specleft features add --format json --id FEATURE_ID --title "Title" [--priority PRIORITY] [--description TEXT] [--dir PATH] [--dry-run] Creates <features-dir>/feature-id.md. Never overwrites existing files. Use --interactive for guided prompts (TTY only).

Add a scenario

specleft features add-scenario --format json --feature FEATURE_ID --title "Title" [--id SCENARIO_ID] [--step "Given ..."] [--step "When ..."] [--step "Then ..."] [--priority PRIORITY] [--tags "tag1,tag2"] [--dir PATH] [--tests-dir PATH] [--dry-run] [--add-test MODE] [--preview-test] Appends to feature file. --add-test generates a test file. --preview-test shows test content without writing. Use --interactive for guided prompts (TTY only).

Status and Planning

Show status

specleft status --format json [--dir PATH] [--feature ID] [--story ID] [--unimplemented] [--implemented]

Next scenario to implement

specleft next --format json [--dir PATH] [--limit N] [--priority PRIORITY] [--feature ID] [--story ID]

Read the full file on GitHub · 115 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago First seen · 115 lines · 0 tokens per session scan A da7b607179f9

Subscribe to this mod's changes

docs is a skill published in the GitHub repository SpecLeft/specleft (3 stars, last pushed 6mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 980 tokens. 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.

Testing ai ai-agents pytest sdd

agentic-test-audit

Audit a pytest suite: surviving mutants and untested code, flaky, order-dependent and slow tests, and removal candidates checked on held-out mutants. Report-only.

sickn33/agentic-awesome-skills · 38 tokens

agentic-verify

Check that a Python change is caught by tests: run every mutant of the changed lines and write tests until they catch them. Reports evidence instead of a diff to read.

sickn33/agentic-awesome-skills · 39 tokens

comet-verify

A workflow for verifying a Comet change after its coding tasks are complete. Comet is a tool that tracks structured software changes through stages.

rpamis/comet · 30 tokens

test-generator

Generate pytest test cases for Python functions and classes.

vstorm-co/pydantic-deepagents · 12 tokens

testing-perf

Performance and load testing patterns — k6 load tests, Locust stress tests, pytest execution optimization (xdist parallel, plugins), test type classification, and performance benchmarking. Use when writing load tests, optimizing test execution speed, or setting up pytest infrastructure.

yonatangross/orchestkit · 55 tokens

implement

Use when an approved plan and task list exist and it is time to turn them into working, tested code — the SDD phase after analyze and before verify. Enforces TDD: a failing test comes before the code that makes it pass, one task at a time, appended to a progress ledger that survives compaction. Delegates test tooling…

ericrisco/rsc-harness · 123 tokens