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.
npx skills add marconae/speq-skill --skill speq-cligit clone --depth 1 https://github.com/marconae/speq-skillWrote 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/skills/marconae/speq-skill/speq-cli)<a href="https://agentmods.dev/skills/marconae/speq-skill/speq-cli"><img src="https://agentmods.dev/badge/skills/marconae/speq-skill/speq-cli/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/skills/marconae/speq-skill/speq-cli"><img src="https://agentmods.dev/badge/skills/marconae/speq-skill/speq-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00664 |
| Opus 5.5 | $0.00000 | $0.00266 |
| Sonnet 5.5 | $0.00000 | $0.00133 |
| Haiku 4.5 | $0.00000 | $0.00066 |
Grade A, and why
speq-cli 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.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
speq CLI
The CLI is installed locally and on the path. Invoke via speq.
Reading Specs
- Find a spec by listing the features with
speq feature list, then read the relevant ones withspeq feature get. - Read a feature with
speq feature get <domain>/<feature>. It prints the description, the Background, and the scenarios. - Read the spec file directly only when exact text matters, and only the lines you need (
Readwith offset and limit).speq feature getdoes not print nested list items under a step or fenced code blocks inside a scenario. - Find before you read:
speq feature get '<domain>/<feature>/<scenario>'for one scenario. Nevercata whole spec.
Command Reference
| Command | Purpose |
|---|---|
speq domain list |
List all domains |
speq feature list |
Tree view of all features |
speq feature list <domain> |
Features in a domain |
speq feature get <domain>/<feature> |
Full feature spec |
speq feature get '<domain>/<feature>/<scenario>' |
Single scenario |
speq decision-log show |
Show every accepted ADR (large in a mature repo; prefer the ADR digest below) |
speq decision-log validate |
Validate the ADR fragments |
speq feature validate |
Validate all specs |
speq feature validate <domain>/<feature> |
Validate single feature |
speq plan list |
List active plans |
speq plan validate <plan> |
Validate a plan |
speq record <plan> |
Merge a validated plan into the permanent specs |
Single-quote a scenario path. In double quotes, the shell runs the text between backticks as a command.
Absence Check
Before you state that no spec or decision covers a topic, run all three steps:
- List the features with
speq feature list. Note each feature whose name relates to the topic or a synonym of it. - Read those candidate features or their scenarios with
speq feature get. - Check the ADR digest (next section). Read only the fragments that match the topic.
Report absence only when all three steps find nothing. Name the features, scenarios, and ADRs you checked in the claim.
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.
- 6d ago Changed · +4 lines 12474ce00669
- 13d ago Changed · +1 lines · -48 tokens per session 1cd61421e89a
- 1mo ago Changed · -17 lines d0e2c9ba690a
- 1mo ago First seen · 67 lines · 48 tokens per session scan A d5a8affb19a9
speq-cli is a skill published in the GitHub repository marconae/speq-skill (55 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 664 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 2026-08-30.
Other skills, from other repositories
build-executor
Execute an active direct request or approved planned change. Native continuous implementation is the default; existing legacy changes retain their recorded contract obligations.
bug-investigator
Use when encountering any bug, test failure, or unexpected behavior during spec-superflow execution, before proposing fixes. Invoked automatically when build-executor hits a blockage.
contract-builder
Maintain an execution contract only for an existing legacy change that requires one. New direct/planned changes do not invoke this skill when a contract is absent.
need-explorer
Clarify intent, scope, constraints, and success criteria before artifact creation. Invoke when the request is fuzzy, the user is comparing options, or the workflow needs a stable change definition before writing artifacts.
plan
Turns a reviewed spec or decided brief into ordered tasks for separate agent runs. Use for implementation tasks, tracker tickets, or useful milestones. Do not use for one coding task or its short execution outline.
code-reviewer
Review completed implementation batches for spec compliance and code quality. Invoke after execution batches complete, before merging, or when a review gate is reached in the workflow.