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/specdog/dotdog/servegit clone --depth 1 https://github.com/specdog/dotdogWhat 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 | $0.00010 | $0.00305 |
| Opus 5 | $0.00005 | $0.00152 |
| Sonnet 5 | $0.00002 | $0.00061 |
| Haiku 4.5 | $0.00001 | $0.00030 |
Grade A, and why
serve 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 yesterday.
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
Serve imported Spec Kit graphs
Prerequisites
- Run this command from the root of the intended Spec Kit project.
- Confirm
dotdog --versionis 0.9.0 or newer. - Confirm
.doghouse/speckit/exists. Run/speckit.dotdog.importfirst when it does not.
User Input
$ARGUMENTS
This command accepts no input. Do not interpolate $ARGUMENTS into a shell command. Stop when any argument is supplied.
Steps
-
Verify
.doghouse/speckit/is a real directory inside the current project root and is not a symlink. -
Compile the imported graphs:
dotdog compile .doghouse/speckit -
Start the local MCP server in the foreground:
dotdog serve .doghouse/speckit -
Keep the process attached exclusively to stdio. When the session ends, stop it normally and leave generated graph files unchanged.
Safety
- Never execute user input as shell text.
- Do not expose a TCP, HTTP, WebSocket, or other network listener.
- Do not add credentials, environment secrets, telemetry, background persistence, or elevated privileges.
- Do not follow symlinks or read outside
.doghouse/speckit/.
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.
- yesterday First seen · 42 lines · 10 tokens per session scan A 13c9df134cd7
serve is a command published in the GitHub repository specdog/dotdog (4 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 305 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
specify
Create or update the feature specification from a natural language feature description.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
constitution
Create or update the project constitution from interactive or provided principle inputs.
tasks
Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
speckit.assess.decide
Apply a go / needs-clarification / kill gate and hand survivors off into Spec-Driven Development.