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/rshade/finfocus/speckit.specifygit clone --depth 1 https://github.com/rshade/finfocusWhat 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 | $0.00013 | $0.02574 |
| Opus 5 | $0.00006 | $0.01287 |
| Sonnet 5 | $0.00003 | $0.00515 |
| Haiku 4.5 | $0.00001 | $0.00257 |
Grade A, and why
speckit.specify 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 3d 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.
This is a copy
70% identical to specify — 185 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
Outline
The text the user typed after /speckit.specify in the triggering message is the feature description. Assume you always have it available in this conversation even if $ARGUMENTS appears literally below. Do not ask the user to repeat it unless they provided an empty command.
Given that feature description, do this:
-
Generate a concise short name (2-4 words) for the branch:
- Analyze the feature description and extract the most meaningful keywords
- Create a 2-4 word short name that captures the essence of the feature
- Use action-noun format when possible (e.g., "add-user-auth", "fix-payment-bug")
- Preserve technical terms and acronyms (OAuth2, API, JWT, etc.)
- Keep it concise but descriptive enough to understand the feature at a glance
- Examples:
- "I want to add user authentication" → "user-auth"
- "Implement OAuth2 integration for the API" → "oauth2-api-integration"
- "Create a dashboard for analytics" → "analytics-dashboard"
- "Fix payment processing timeout bug" → "fix-payment-timeout"
-
Create branch and spec directory using the script:
Run the script with just the short-name (let the script auto-detect the next available number):
.specify/scripts/bash/create-new-feature.sh --json --short-name "<short-name>" "<feature description>"Examples:
.specify/scripts/bash/create-new-feature.sh --json --short-name "user-auth" "Add user authentication".specify/scripts/bash/create-new-feature.sh --json --short-name "oauth2-api" "Implement OAuth2 integration"
IMPORTANT:
- Do NOT pass
--number- the script automatically finds the highest number across ALL branches and specs globally and uses the next available number - The script handles: fetching remotes, scanning all branches (local + remote), scanning specs directory
- You must only ever run this script once per feature
- The JSON output contains BRANCH_NAME and SPEC_FILE paths - use these values
- For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'''m Groot' (or double-quote if possible: "I'm Groot")
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.
- 3d ago First seen · 245 lines · 13 tokens per session scan A 17509a74ae50
speckit.specify is a command published in the GitHub repository rshade/finfocus (5 stars, last pushed 17d ago), licensed Apache-2.0. It adds 13 tokens to every session and 2,574 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 70% identical to specify, differing in 185 lines, and is treated as a copy.
Other commands, from other repositories
pr-review
Review a pull request — gather metadata, diff, and existing feedback, then give a verdict.
scan
Scan AWS account for cost optimization.
costguard-audit
Audit registered workspaces for CI-minute and cron waste, plus read-only cloud provider billing checks. Quantifies estimated monthly waste and prints a Markdown (or JSON) report.
coaching-conversation-patterns
AI coaching and conversational support — empathetic interactions, safety guardrails, motivational interviewing, SMART goals, and crisis handling for coaching, therapy, education, or customer support. Use when building a coaching or support conversation, adding safety guardrails, or handling sensitive user disclosures.…
langfuse-observability
LLM observability with self-hosted Langfuse — tracing, evaluation, prompt versioning, cost tracking, and LLM-as-judge scoring. Use when adding LLM tracing, monitoring token cost, versioning prompts, or building evaluation dashboards. Triggers on Langfuse, LLM observability, tracing, prompt versioning, cost tracking…
streaming-api-patterns
Real-time data streaming with SSE, WebSockets, and ReadableStream. Use when implementing token streaming, Server-Sent Events, backpressure handling, or reconnection strategies. Triggers on streaming, SSE, Server-Sent Events, WebSocket, ReadableStream, backpressure, reconnection, token streaming.