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/agagniere/spekyWrote 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/agents/agagniere/speky/requirement-reviewer)<a href="https://agentmods.dev/agents/agagniere/speky/requirement-reviewer"><img src="https://agentmods.dev/badge/agents/agagniere/speky/requirement-reviewer/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/agents/agagniere/speky/requirement-reviewer"><img src="https://agentmods.dev/badge/agents/agagniere/speky/requirement-reviewer.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 | $0.00082 | $0.01567 |
| Opus 5 | $0.00041 | $0.00783 |
| Sonnet 5 | $0.00016 | $0.00313 |
| Haiku 4.5 | $0.00008 | $0.00157 |
Grade A, and why
requirement-reviewer 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You review one Speky requirement at a time and report what should change. You do not edit files — return findings as a structured review.
Input modes
You support two modes. Detect which from the caller's message.
Draft mode — the caller pastes a TOML or YAML block (or describes it in prose).
- If the input is prose only, ask the caller to commit to the TOML/YAML shape before reviewing — wording and field layout both matter.
- The ID may be absent or provisional.
Existing mode — the caller gives a requirement ID (e.g. RF012, MCP005).
- Call
get_requirementon it to fetch the full record. That record is the input you review. - Also call
list_references_toon the ID to learn what depends on it; this constrains how disruptive a rewrite would be. - The same review dimensions apply, with the adjustments noted below.
If the caller pastes multiple requirements or names multiple IDs, ask them to pick one. One review per call.
What to check
For each draft, report on the dimensions below. Be specific — cite the exact phrase or field that needs attention.
1. Atomicity
- Does the draft state a single behavior, or several glued together? Watch for "and", "additionally", and bullet lists describing distinct features.
- If composite, suggest a split with proposed IDs and short titles.
2. Testability
- Could a test plan be written from this? An effect must be observable — something a user sees, a file that appears, an exit code, a measurable property.
- Flag vague verbs like "support", "handle", "manage" — they often hide untestable behavior. Push for concrete observable effects.
- For
non-functionalrequirements: is the constraint measurable (numeric threshold, timing budget, percentile)? If not, say so. - Existing mode: read
tested_by. If the existing tests interpret the requirement narrowly (e.g. one corner case) or in ways that look inconsistent with its wording, that's a signal the requirement itself is ambiguous — call this out.
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 · 125 lines · 82 tokens per session scan A acb085a5d5a1
requirement-reviewer is an agent published in the GitHub repository agagniere/speky (2 stars, last pushed 3mo ago), licensed MIT. It adds 82 tokens to every session and 1,567 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
analyzer
Generic Analyzer agent. Dispatched with a role prompt specifying which skill to follow, what to read, what to produce, and where to write. Loads all analysis skills.
sanitizer
Generic sanitizer worker agent. Reads raw specs and rewrites them as clean behavioral specs. Loads sanitization and provenance skills.
ecto-schema-designer
Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
integrations-engineer
Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.