Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/arrrrny/zuraffanpx agentmods add commands/arrrrny/zuraffa/speckit.md-doctor.applyWrote 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/arrrrny/zuraffa/speckit.md-doctor.apply)<a href="https://agentmods.dev/commands/arrrrny/zuraffa/speckit.md-doctor.apply"><img src="https://agentmods.dev/badge/commands/arrrrny/zuraffa/speckit.md-doctor.apply/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/commands/arrrrny/zuraffa/speckit.md-doctor.apply"><img src="https://agentmods.dev/badge/commands/arrrrny/zuraffa/speckit.md-doctor.apply.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 | $0.00028 | $0.00843 |
| Opus 5.5 | $0.00011 | $0.00337 |
| Sonnet 5.5 | $0.00006 | $0.00169 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
speckit.md-doctor.apply 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.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MD Doctor — Apply
Mechanically act on the suggestions MD Doctor recorded during scan/drift. It is
deliberately conservative: by default it only does safe things (create stubs for
missing docs, stamp verified docs). Deletion is destructive and requires an explicit
flag.
User Input
$ARGUMENTS
Recognized modifiers:
--action create— only create the missing-doc stubs.--action stamp— only append a "verified" footer to keep/update docs.--action delete— show the delete plan (destructive; see--delete).--delete— actually delete files the engine markeddelete. Destructive.--all— do everything (create + stamp + delete); implies--delete.
With no flag, the safe default runs: create stubs + stamp verified docs. No deletes.
Preconditions
A scan (or drift) must have run so .specify/md-doctor/state/facts.json exists
with action fields. If missing, stop and tell the user to run
/speckit.md-doctor.scan first.
Workflow
Phase 1: Run the engine
bash .specify/extensions/md-doctor/scripts/bash/md-doctor.sh apply [--delete] [--action <a>] [--all]
(Dev fallback: bash <extension-root>/md-doctor/scripts/bash/md-doctor.sh apply ....)
What it does, by flag:
- default — for each
createfact, write a stub atproposed_path; for eachkeep/updatefact, append a footer> Verified by md-doctor on <date> — truthfulness <n>/100.(idempotent: skips files stamped today). --action create— stubs only.--action stamp— footers only.--action delete(no--delete) — prints the files it would delete; changes nothing.--delete— also removes files markeddelete.--all— create + stamp + delete.
Phase 2: Review the engine output
The engine prints created=N stamped=N deleted=N and the affected paths. Read them.
If --delete was used, confirm the deleted paths are exactly the false/obsolete
docs from the last report and nothing else. If something looks wrong, you may restore
from git (git checkout -- <path> / git restore) since deletes are working-tree
only until committed.
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 · 86 lines · 28 tokens per session scan A 7e9f99acbd43
speckit.md-doctor.apply is a command published in the GitHub repository arrrrny/zuraffa (5 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 843 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 2026-09-03.
Other commands, from other repositories
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
session-end
I'll summarize this coding session and update the memory system with our accomplishments.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.