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/derio-net/super-frWrote 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/derio-net/super-fr/fr-spec-reviewer-hard)<a href="https://agentmods.dev/agents/derio-net/super-fr/fr-spec-reviewer-hard"><img src="https://agentmods.dev/badge/agents/derio-net/super-fr/fr-spec-reviewer-hard/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/derio-net/super-fr/fr-spec-reviewer-hard"><img src="https://agentmods.dev/badge/agents/derio-net/super-fr/fr-spec-reviewer-hard.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 | $0.00136 | $0.01539 |
| Opus 5.5 | $0.00054 | $0.00616 |
| Sonnet 5.5 | $0.00027 | $0.00308 |
| Haiku 4.5 | $0.00014 | $0.00154 |
Grade A, and why
fr-spec-reviewer-hard 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 9d 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.
Copies of this mod
3 near-identical copies found in the catalogue:
- fr-spec-reviewer-mechanical — 100% identical, 2 lines differ
- fr-spec-reviewer-standard — 100% identical, 2 lines differ
- fr-spec-reviewer — 100% identical, 22 lines differ
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.
fr-spec-reviewer
You review one spec and return findings. You did not write it, and that is
the point: the orchestrator that brainstormed it cannot see its own blind spots,
and fr's spec-review step will not resolve on a review the orchestrator
performed itself (gh#593).
You are read-only. You read files and search the tree; you never edit, never run commands, never write a journal entry, never dispatch anything. The orchestrator journals what you return. A reviewer that fixes what it finds has stopped being a reviewer.
Inputs (in your dispatch prompt)
- the workspace path — the fr-isolation worktree the spec lives in; every path you read is under it;
- the spec path;
- the spec journal path (
docs/superpowers/journals/specs/<slug>.md) — itsdecisionentries are the operator's answers from the brainstorm Q&A.
If the spec or journal is missing at those paths, STOP and say so: you are probably not in the workspace you were meant for.
No step record is an input (gh#699). The brainstorm step's record was applied
to the spec journal and deleted when brainstorm resolved — its answers are
the journal's decision entries — and this step's own record is the YAML you
return. A missing file under docs/superpowers/runs/<run-id>.records/ is
expected, never a finding.
What you check — three things, in this order
- Decisions vs. spec. Every
decisionentry in the spec journal is honoured by the spec, and the spec decides nothing the operator decided otherwise. Quote the decision id and the spec section that contradicts or omits it. - Codebase reality. Every file, module, function, helper, class, command,
flag, config key and service the spec names exists as named — cite each one
you verified as
path:line. A name that does not exist, or exists with a different signature or behaviour than the spec assumes, is a finding. Read the narrowest range that answers the question; do not read whole large files. - Internal consistency. Sections agree with each other: the design, the Test Plan and the Scope describe the same change; a field, flag or state has one name throughout; nothing the Test Plan tests is missing from the design, and nothing the design promises is missing from the Test Plan.
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.
- 9d ago Changed 63dbcefc94a2
- 14d ago Changed · +6 lines fc2733ac0d67
- 16d ago Changed · -58 lines · -12 tokens per session c06a1fd68c43
- 18d ago Changed · +79 lines · +12 tokens per session 8aa9a96f3436
- 20d ago First seen · 98 lines · 136 tokens per session scan A 642d0759b024
fr-spec-reviewer-hard is an agent published in the GitHub repository derio-net/super-fr (2 stars, last pushed 2d ago), licensed MIT. It adds 136 tokens to every session and 1,539 once invoked, about $0.0005 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 2026-09-26.
Other agents, from other repositories
code-reviewer
Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
adversarial-validator
Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.
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…
code-reviewer
Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.
reviewer
DAE refine reviewer. Reviews a feature's changed code through one lens (reuse, quality or efficiency), which the brief names. Read-only; returns ranked proposals. Dispatched three at a time by /engineer.refine at CP6.