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.
git clone --depth 1 https://github.com/marcusgoll/Spec-FlowWrote 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/constitution)<a href="https://agentmods.dev/commands/marcusgoll/spec-flow/constitution"><img src="https://agentmods.dev/badge/commands/marcusgoll/spec-flow/constitution/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/constitution"><img src="https://agentmods.dev/badge/commands/marcusgoll/spec-flow/constitution.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 | $0.00024 | $0.04823 |
| Opus 5.5 | $0.00010 | $0.01929 |
| Sonnet 5.5 | $0.00005 | $0.00965 |
| Haiku 4.5 | $0.00002 | $0.00482 |
Grade A, and why
constitution 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 — 657 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/constitution — Update Engineering Principles
Current Git Status: !git status --short 2>/dev/null || echo "clean"
Current Branch: !git branch --show-current 2>/dev/null || echo "none"
Principles File Exists: !test -f docs/project/engineering-principles.md && echo "Yes" || echo "No"
Principles File: @docs/project/engineering-principles.md
Recent Constitution Commits: !git log --oneline --grep="constitution:" -5 2>/dev/null || echo "none"
Purpose: Modify quality gates, add/update/remove principles, and maintain governance metadata with version control.
When to use:
- Add, remove, or revise a principle
- Tighten quality gates (security, accessibility, performance, tests)
- Align standards with new evidence or incidents
- Bump principle document version
Workflow position: Project governance command. Downstream gates (/optimize, /validate, /ship) enforce these principles.
Anti-Hallucination Rules
CRITICAL: Follow these rules to prevent implementation errors.
-
Never modify the file without reading it first
- Always Read docs/project/engineering-principles.md before making changes
- Verify file structure matches canonical template
- Quote current content when analyzing changes
-
Verify file existence before proceeding
- Use Grep to check file exists
- If not found, instruct user to run /init-project first
- Don't assume file structure - read and verify
-
Validate principle structure after changes
- Check for required headers (## Principles)
- Verify principle IDs match pattern:
### [ID] Title - Ensure all required fields present (Policy, Rationale, Measurable checks, Evidence, Last updated)
-
Quote arguments exactly
- Parse $ARGUMENTS precisely without adding interpretation
- If arguments unclear, show usage examples and ask for clarification
- Never guess at action types or field values
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 · 657 lines · 24 tokens per session scan A 835b00af45b4
constitution is a command published in the GitHub repository marcusgoll/Spec-Flow (96 stars, last pushed 24d ago), licensed MIT. It adds 24 tokens to every session and 4,823 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 2026-08-30.
Other commands, from other repositories
check
Checks if the code is ready to be committed.
sync
Stage, commit, and push pending changes via the gss skill in one guided flow.
commit
Commit current changes following project commit rules (template, body settings).
run-task
Run pending steps, then aftertask finalization; does not close the task.
finish-task
Deprecated alias for close-task.
gh-review-fix-loop
Fix and resolve GitHub PR review threads.