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 agentmods add commands/gregorbiswanger/featherspec/sdd-featherspec-updategit 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/commands/gregorbiswanger/featherspec/sdd-featherspec-update)<a href="https://agentmods.dev/commands/gregorbiswanger/featherspec/sdd-featherspec-update"><img src="https://agentmods.dev/badge/commands/gregorbiswanger/featherspec/sdd-featherspec-update.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.08367 |
| Opus 5 | $0.00012 | $0.04183 |
| Sonnet 5 | $0.00005 | $0.01673 |
| Haiku 4.5 | $0.00002 | $0.00837 |
Grade A, and why
sdd-featherspec-update 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 6d 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 — 495 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sdd-featherspec-update — Template Version Check & Safe Update
Template source: https://github.com/GregorBiswanger/featherspec — forks that maintain their
own template change this one line.
The user may type an argument after the command: check runs the version check only (no
writes, no fetch unless the user wants the latest-version lookup); a version like 1.3.0
targets that release; nothing means latest. Speak plainly, in DocLanguage, throughout;
wiring you write stays English.
The safety contract, in one paragraph. This workflow updates FeatherSpec's own wiring in
this project — never the project's knowledge. It compares three states of every file: Base
(the template version this project came from), Target (the version to update to) and
Project (what is on disk). Base and Target are fetched as real trees, so no maintained
metadata can mis-classify a file. Whatever the comparison cannot prove is asked, never
assumed: unknown means ask, never overwrite. User data (.memory-bank/, .specs/
content, .architecture/, README.md, LICENSE, CHANGELOG.md, docs/, the logo —
featherspec-logo.png or whatever image replaced it — and every *.local.* file) is a
never-write set: hashed before, proven byte-identical after. The
version stamp moves last — an interrupted run always identifies as the old version with
work in flight.
Where am I? (state router — the files decide, not the conversation)
- Argument
check→ run Version check below, report, stop. .sdd-update/_state.mdexists → this is a resume. Read_state.mdfirst; if it names agoverning-body:path, read that file now and follow it for the rest of the run — it is the newer updater fetched last session. Resume runs before any dirty-tree check. If the user asks for a different target than_state.mdrecords, say so, discard the state and restart. On resume under a different shell than_state.mdrecords, re-run the hash scripts instead of trusting stored hashes.- Otherwise → fresh run, Phase 0.
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.
- 6d ago First seen · 495 lines · 24 tokens per session scan A 4e20dbdc17e8
sdd-featherspec-update is a command published in the GitHub repository GregorBiswanger/featherspec (47 stars, last pushed 7d ago), licensed MIT. It adds 24 tokens to every session and 8,367 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
spec-kitty-standalone
This host should read Spec Kitty's canonical standalone-invocation skill pack at.
spec-kitty.implement
Spec-Driven Development for serious software developers. Spec Coding with with Claude, Cursor, Gemini, Codex. Kanban dashboard, git worktrees, auto-merge and more.
spec-kitty.research
Spec-Driven Development for serious software developers. Spec Coding with with Claude, Cursor, Gemini, Codex. Kanban dashboard, git worktrees, auto-merge and more.
spec-kitty.tasks-outline
Spec-Driven Development for serious software developers. Spec Coding with with Claude, Cursor, Gemini, Codex. Kanban dashboard, git worktrees, auto-merge and more.
spec-kitty.tasks-packages
Spec-Driven Development for serious software developers. Spec Coding with with Claude, Cursor, Gemini, Codex. Kanban dashboard, git worktrees, auto-merge and more.
spec-kitty.analyze
Spec-Driven Development for serious software developers. Spec Coding with with Claude, Cursor, Gemini, Codex. Kanban dashboard, git worktrees, auto-merge and more.