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/gszhangwei/open-spddWrote 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/gszhangwei/open-spdd/spdd-prompt-update)<a href="https://agentmods.dev/commands/gszhangwei/open-spdd/spdd-prompt-update"><img src="https://agentmods.dev/badge/commands/gszhangwei/open-spdd/spdd-prompt-update/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/gszhangwei/open-spdd/spdd-prompt-update"><img src="https://agentmods.dev/badge/commands/gszhangwei/open-spdd/spdd-prompt-update.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 | $0.00027 | $0.02138 |
| Opus 5 | $0.00014 | $0.01069 |
| Sonnet 5 | $0.00005 | $0.00428 |
| Haiku 4.5 | $0.00003 | $0.00214 |
Grade A, and why
/spdd-prompt-update 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 9d 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update an existing SPDD (Structured Prompt-Driven Development) prompt file with new requirements, architectural changes, or refinements while maintaining the REASONS Canvas structure and following all specification rules.
Input: The argument after /spdd-prompt-update includes the prompt file reference and the update instructions.
Examples:
# Update with architectural principles
/spdd-prompt-update @spdd/prompt/GGQPA-XXX-202603131758-[Feat]-api-token-usage-billing.md
Add three-layer architecture with dependency inversion principle
# Update with new requirements
/spdd-prompt-update @spdd/prompt/GGQPA-XXX-202603131758-[Feat]-api-token-usage-billing.md
Add support for batch usage submission
# Update specific section
/spdd-prompt-update @spdd/prompt/GGQPA-XXX-202603131758-[Feat]-api-token-usage-billing.md
Update Safeguards section to add rate limiting constraints
Steps
-
Validate input
a. If no prompt file provided, use the AskUserQuestion tool to ask:
"Please provide the path to the SPDD prompt file to update (e.g.,
@spdd/prompt/xxx.md)"b. If no update instructions provided, use the AskUserQuestion tool to ask:
"What changes would you like to make to this prompt? (e.g., new requirements, architectural changes, constraint updates)"
IMPORTANT: Do NOT proceed without both the file path and update instructions.
-
Read and analyze the existing prompt
a. Read the entire SPDD prompt file b. Identify all existing REASONS sections:
- Requirements
- Entities
- Approach
- Structure
- Operations
- Norms
- Safeguards c. Understand the current architecture, entities, and constraints
-
Analyze the update request
Determine which sections need to be updated based on the change request:
Change Type Affected Sections New functional requirement R, E, A, S, O, possibly N, S Architectural change A, S, O, N New entity/relationship E, S, O New constraint/safeguard S (Safeguards), possibly O Coding standard change N, O Bug fix in specification Targeted section only -
Read relevant codebase context (if needed)
If the update involves:
- New entities → Read existing entity classes
- New patterns → Read existing similar implementations
- New integrations → Read related services/repositories
-
Apply updates to affected sections
For each affected section:
a. Preserve unchanged content - Do NOT rewrite sections that don't need changes b. Integrate changes coherently - Ensure new content fits with existing content c. Maintain consistency - Cross-check that changes are reflected across related sections d. Follow REASONS construction guidance - Apply the same quality standards as initial generation
Section-specific guidance:
- Requirements: Update if business goal changes
- Entities: Add/modify entities, update Mermaid diagram
- Approach: Update strategies, add new architectural decisions
- Structure: Update inheritance, dependencies, layered architecture
- Operations: Add new operations, modify existing operation specifications
- Norms: Add new standards, update package structure
- Safeguards: Add new constraints, update existing rules
-
Validate cross-section consistency
After updates, verify:
- Entities mentioned in Operations exist in Entities section
- Dependencies in Structure match what's described in Operations
- Constraints in Safeguards are enforceable based on Operations
- Norms are applied consistently across Operations
-
Write the updated prompt file
a. Overwrite the existing file with the updated content b. Preserve the original filename (do NOT rename)
-
Show update summary
✅ SPDD prompt updated: `spdd/prompt/<file-name>.md` 📋 Changes made: - [Section]: [Summary of changes] - [Section]: [Summary of changes] 🔍 Sections unchanged: - [List of sections that were not modified] ⚠️ Review recommendations: - [Any areas that may need manual review]
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.
- 9d ago First seen · 227 lines · 27 tokens per session scan A 4bc3d00bae52
/spdd-prompt-update is a command published in the GitHub repository gszhangwei/open-spdd (740 stars, last pushed 18d ago), licensed MIT. It adds 27 tokens to every session and 2,138 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 2026-08-30.
Other commands, from other repositories
specify
Create or update the feature specification from a natural language feature description.
constitution
Create or update the project constitution from interactive or provided principle inputs.
plan
Execute the implementation planning workflow using the plan template to generate design artifacts.
speckit.bug.test
Validate that a previously fixed bug is resolved and record the verification report.
speckit.git.validate
Validate current branch follows feature branch naming conventions.
speckit.agent-context.update
Refresh the managed Spec Kit section in coding agent context file(s).