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/marcusgoll/Spec-Flownpx agentmods add commands/marcusgoll/spec-flow/quickWrote 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/marcusgoll/spec-flow/quick)<a href="https://agentmods.dev/commands/marcusgoll/spec-flow/quick"><img src="https://agentmods.dev/badge/commands/marcusgoll/spec-flow/quick/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/marcusgoll/spec-flow/quick"><img src="https://agentmods.dev/badge/commands/marcusgoll/spec-flow/quick.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 | $0.00041 | $0.03867 |
| Opus 5.5 | $0.00016 | $0.01547 |
| Sonnet 5.5 | $0.00008 | $0.00773 |
| Haiku 4.5 | $0.00004 | $0.00387 |
Grade A, and why
quick 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 — 516 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRITICAL ARCHITECTURE (v2.0 - Task() Orchestrator Pattern):
This orchestrator is lightweight. You MUST:
- Parse arguments and validate scope (inline)
- Create branch (inline)
- Spawn isolated quick-worker agent via Task tool
- Handle Q&A when agent returns
---NEEDS_INPUT--- - Display summary from agent result
Benefits: Implementation is isolated, Q&A flows naturally, consistent with /feature and /epic patterns.
Current branch:
!git branch --show-current
Recent commits (last 3):
!git log -3 --oneline
Studio context (multi-agent isolation):
!bash .spec-flow/scripts/bash/worktree-context.sh studio-detect 2>/dev/null || echo ""
Worktree context:
!bash .spec-flow/scripts/bash/worktree-context.sh info 2>/dev/null || echo '{"is_worktree": false}'
<when_to_use>
Good Candidates (Use /quick)
- Bug fixes: UI glitches, logic errors, null checks
- Small refactors: Rename variables, extract functions, simplify logic
- Internal improvements: Logging, error messages, constants
- Documentation: README updates, code comments, docstrings
- Style/formatting: Whitespace, naming conventions, linting fixes
- Config tweaks: Environment variables, build settings, tool configs
Characteristics: <100 LOC, <5 files, single concern, no breaking changes, can implement in one sitting
Do NOT Use (Use /feature Instead)
- New features with UI components - Needs design review and mockup approval
- Database schema changes - Requires migration planning and zero-downtime strategy
- API contract changes - Breaking changes need stakeholder review
- Security-sensitive code - Auth, permissions, crypto need thorough review
- Changes affecting >5 files - Coordination across modules needs planning
- Multi-step features - Complex workflows need task breakdown
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 · 516 lines · 41 tokens per session scan A 5b8c8d9cf97c
quick is a command published in the GitHub repository marcusgoll/Spec-Flow (96 stars, last pushed 24d ago), licensed MIT. It adds 41 tokens to every session and 3,867 once invoked, about $0.0002 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 commands, from other repositories
sync-linear
Sync current work with Linear ticket status.
task-verify
PitWay: Run an inprogress task's approved verification command and persist evidence.
milestone-list
PitWay: List every milestone with a concise one-line status.
amp-register
Register your agent with an external AMP provider for cross-provider messaging.
amp-identity
Quick identity check for context recovery. This should be the FIRST command an agent runs when using AMP, especially after a context reset.
example
Example command that demonstrates CodexSpec extension functionality.