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.
git clone --depth 1 https://github.com/ariel-frischer/autospecWrote 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.
[](https://agentmods.dev/commands/ariel-frischer/autospec/autospec.analyze)<a href="https://agentmods.dev/commands/ariel-frischer/autospec/autospec.analyze"><img src="https://agentmods.dev/badge/commands/ariel-frischer/autospec/autospec.analyze/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.
<a href="https://agentmods.dev/commands/ariel-frischer/autospec/autospec.analyze"><img src="https://agentmods.dev/badge/commands/ariel-frischer/autospec/autospec.analyze.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00011 | $0.02029 |
| Opus 5 | $0.00005 | $0.01014 |
| Sonnet 5 | $0.00002 | $0.00406 |
| Haiku 4.5 | $0.00001 | $0.00203 |
Grade A, and why
autospec.analyze 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 251 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).
Goal
Identify inconsistencies, duplications, ambiguities, and underspecified items across the core artifacts (spec, plan, tasks) before implementation. This command MUST run only after /autospec.tasks has successfully produced a complete tasks file.
Operating Constraints
STRICTLY READ-ONLY: Do not modify any files. Output a structured analysis YAML file. Offer an optional remediation plan (user must explicitly approve before any follow-up editing commands would be invoked manually).
Constitution Authority: The project constitution (.autospec/constitution.yaml or AGENTS.md, falling back to agent-specific file like CLAUDE.md) is non-negotiable within this analysis scope. Constitution conflicts are automatically CRITICAL and require adjustment of the spec, plan, or tasks.
Pre-computed Context
The following paths have been pre-computed and are available for use:
- FEATURE_DIR:
{{.FeatureDir}} - FEATURE_SPEC:
{{.FeatureSpec}}
Execution Steps
1. Load Artifacts (Progressive Disclosure)
Load only the minimal necessary context from each artifact:
From spec.yaml:
- Overview/Context
- Functional Requirements
- Non-Functional Requirements
- User Stories
- Edge Cases (if present)
From plan.yaml:
- Architecture/stack choices
- Data Model references
- Phases
- Technical constraints
From tasks.yaml:
- Task IDs
- Descriptions
- Phase grouping
- Parallel markers
- Referenced file paths
From constitution:
- Load
.autospec/constitution.yamlorAGENTS.md(falling back to agent-specific file likeCLAUDE.md) for principle validation
2. Build Semantic Models
Create internal representations (do not include raw artifacts in output):
- Requirements inventory: Each functional + non-functional requirement with a stable key
- User story/action inventory: Discrete user actions with acceptance criteria
- Task coverage mapping: Map each task to one or more requirements or stories
- Constitution rule set: Extract principle names and MUST/SHOULD normative statements
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.
- 10d ago First seen · 251 lines · 11 tokens per session scan A cb7547ca9e39
autospec.analyze is a command published in the GitHub repository ariel-frischer/autospec (141 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 2,029 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.
Other commands, from other repositories
speckit.companion.implement
Companion implement — execute tasks.md in dependency order, then mark complete.
speckit.companion.plan
Companion plan — implementation plan with research & design artifacts.
speckit.companion.doctor
Report on a spec's run health — unfinished steps, unjournaled tasks, step bleed, drift you can judge, a step that closed having verified nothing, a step that closed without the file it promised, and why completion did not land (read-only, retroactive, never halts).
speckit.companion.living-move
Move a living spec between central and colocated storage — file, tiers, and registry together (opt-in, reversible).
speckit.companion.living-validate
Check the shape of living specs and a feature spec's deltas — a requirement with no scenario, a scenario missing WHEN or THEN, a duplicate heading, a delta pointing at nothing (opt-in, read-only, never halts).
speckit.companion.after-specify
Capture the current spec-kit step into .spec-context.json for the Companion GUI.