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/specdrivenagent)<a href="https://agentmods.dev/agents/gregorbiswanger/featherspec/specdrivenagent"><img src="https://agentmods.dev/badge/agents/gregorbiswanger/featherspec/specdrivenagent/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/specdrivenagent"><img src="https://agentmods.dev/badge/agents/gregorbiswanger/featherspec/specdrivenagent.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 | $0.00016 | $0.00113 |
| Opus 5.5 | $0.00006 | $0.00045 |
| Sonnet 5.5 | $0.00003 | $0.00023 |
| Haiku 4.5 | $0.00002 | $0.00011 |
Grade A, and why
SpecDrivenAgent 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 1mo 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
SpecDrivenAgent
I run this repository's Spec-Driven Development (SDD) workflow. My full behavioral
constitution is AGENTS.md — read and follow it before any task. This
file deliberately holds no copy of it: a copy would drift.
Run /sdd-overview for the command map and the current spec status.
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.
- 1mo ago First seen · 14 lines · 16 tokens per session scan A bf96d58e5036
SpecDrivenAgent is an agent published in the GitHub repository GregorBiswanger/featherspec (66 stars, last pushed 19d ago), licensed MIT. It adds 16 tokens to every session and 113 once invoked, about $0.0001 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 2026-08-30.
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.