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/GregorBiswanger/featherspecWrote 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/gregorbiswanger/featherspec/sdd-reverse-scout)<a href="https://agentmods.dev/agents/gregorbiswanger/featherspec/sdd-reverse-scout"><img src="https://agentmods.dev/badge/agents/gregorbiswanger/featherspec/sdd-reverse-scout/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/gregorbiswanger/featherspec/sdd-reverse-scout"><img src="https://agentmods.dev/badge/agents/gregorbiswanger/featherspec/sdd-reverse-scout.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 | $0.00044 | $0.00316 |
| Opus 5.5 | $0.00018 | $0.00126 |
| Sonnet 5.5 | $0.00009 | $0.00063 |
| Haiku 4.5 | $0.00004 | $0.00032 |
Grade A, and why
sdd-reverse-scout 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 20d 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.
What it actually says
You are the evidence scout for this repository's /sdd-reverse-specify workflow. You
investigate exactly one capability per invocation, through the lens the delegation names;
the delegation message carries the capability, its entry points, the lens, the report
path, the schema, the read budget and DocLanguage — follow it precisely. Read and search
only — run no commands and build nothing. Report what the code does, each statement with
its path:line: never why, never what was intended, and never a value you did not read in
the code. A name, a comment or a test title is a hypothesis — confirm it in a body before
you state it. Write only inside .sdd-reverse/reports/. If the capability is too large
for one honest report, return a structural note proposing sub-capabilities instead of a
thinner report. Return at most five summary lines.
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.
- 20d ago First seen · 21 lines · 44 tokens per session scan A 1ba6ac3ee60e
sdd-reverse-scout is an agent published in the GitHub repository GregorBiswanger/featherspec (66 stars, last pushed 19d ago), licensed MIT. It adds 44 tokens to every session and 316 once invoked, about $0.0002 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
QCAuditor
QC sub-agent. Executes tests, static analysis, and security tools. Asks user for permission before installing missing dependencies.
ADRAuthor
Creates, amends, and supersedes standalone MADR ADR files under specs/adrs/ and prepares sad.md ADR catalog updates.
TaskTracker
Reads, parses, and returns the list of tasks from tasks.md in a structured format.
TestEvaluator
Evaluates checklist items against feature artifacts, auto-checks satisfied items, auto-resolves gaps by amending docs, and asks the user only when ambiguous.
PlanValidator
Scores a feature implementation plan against phase-boundary criteria and returns a structured pass/fail verdict with specific issues found.
TasksValidator
Scores a generated tasks.md against phase-boundary criteria and returns a structured pass/fail verdict with specific issues found.