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-adr-rulesgit 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-adr-rules)<a href="https://agentmods.dev/skills/marconae/speq-skill/speq-adr-rules"><img src="https://agentmods.dev/badge/skills/marconae/speq-skill/speq-adr-rules/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-adr-rules"><img src="https://agentmods.dev/badge/skills/marconae/speq-skill/speq-adr-rules.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 | $0.00076 | $0.01458 |
| Opus 5.5 | $0.00030 | $0.00583 |
| Sonnet 5.5 | $0.00015 | $0.00292 |
| Haiku 4.5 | $0.00008 | $0.00146 |
Grade A, and why
speq-adr-rules 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 3d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADR Rules
An ADR is a rare record of a durable decision. Most plans produce none. This skill is the single owner of the rules. Other skills and agents cite it and do not restate it.
1. Default No
- The expected number of
Promotes to ADR: yesentries per plan is zero. - Set
yesonly when a criterion in rule 2 applies and you can name it. - Two or more
yesentries in one plan get re-judged. Re-read each one against rule 2 and rule 3 before you keep it. - A plan with many Design Decisions entries or many resolved review findings does not owe an ADR for each. Most decisions are local and stay
no.
2. Criteria for Yes
A decision qualifies only when at least one of these holds:
- It affects multiple components or teams.
- It sets a long-lived constraint that binds future work.
- It is a major technology, API, persistence, security, or deployment choice.
- It rejects a plausible alternative, and the reason will matter to a later reader.
The entry's Rationale names the criterion that applies and states the result of the search in rule 5.
3. Never an ADR
- Naming, file placement, and folder layout.
- A one-off bug fix.
- A scope trim or a task ordering choice.
- Implementation detail: function signatures, file paths, flags, data layout inside one module.
- A workaround specific to one plan's own mechanics, such as a spec-merge gap or a review-loop correction.
- A corollary of another decision. Record it as a bullet in the parent entry's Consequences line.
- A statement that already lives in a feature spec scenario.
4. Where It Goes Instead
| Content | Destination |
|---|---|
| Conventions that bind contributors or agents | CLAUDE.md, AGENTS.md, a .speq/*-hook.md file, or specs/mission.md Constraints |
| WHAT the system is: components and boundaries | specs/architecture.md, changed through an architecture delta |
| HOW this plan builds it | A phrase in the plan.md task line. Only a choice with a rejected alternative gets a decision-log.md ## Design Decisions entry with Promotes to ADR: no |
| Execution steps | plan.md ## Implementation Tasks |
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.
- 3d ago Changed · +10 tokens per session 4a7cd9653956
- 10d ago Changed · +14 lines 520eb1c3e76a
- 13d ago First seen · 86 lines · 66 tokens per session scan A 6dc35cd5dc0c
speq-adr-rules is a skill published in the GitHub repository marconae/speq-skill (55 stars, last pushed 4d ago), licensed MIT. It adds 76 tokens to every session and 1,458 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-03.
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.