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/gszhangwei/open-spdd/spdd-syncgit 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-sync)<a href="https://agentmods.dev/commands/gszhangwei/open-spdd/spdd-sync"><img src="https://agentmods.dev/badge/commands/gszhangwei/open-spdd/spdd-sync.svg" alt="Measured on agentmods" 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 | $0.00022 | $0.02424 |
| Opus 5 | $0.00011 | $0.01212 |
| Sonnet 5 | $0.00004 | $0.00485 |
| Haiku 4.5 | $0.00002 | $0.00242 |
Grade A, and why
/spdd-sync 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 4d 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 — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synchronize implementation details from refactored or updated code back to the structured SPDD (Structured Prompt-Driven Development) prompt file, ensuring the prompt remains the accurate source of truth for the system design.
Input: The argument after /spdd-sync is the path to the structured prompt file (e.g., @spdd/prompt/GGQPA-XXX-202602271430-[Feat]-api-create-agent-endpoint.md).
Steps
-
If no input provided, ask for the prompt file
Use the AskUserQuestion tool to ask:
"Please provide the path to the structured prompt file you want to sync (e.g.,
@spdd/prompt/xxx.md)."IMPORTANT: Do NOT proceed without a valid prompt file path.
-
Read and parse the structured prompt file
Read the prompt file and identify the REASONS Canvas sections:
Section Purpose Sync Priority R - Requirements Overall goal and DoD Low (rarely changes from code) E - Entities Domain model and relationships High (class diagrams may change) A - Approach Implementation strategy Medium (architectural decisions) S - Structure Components and dependencies High (inheritance/dependencies change) O - Operations Concrete implementation tasks Highest (implementation details) N - Norms Engineering standards Medium (patterns may evolve) S - Safeguards Non-negotiable constraints Low (constraints rarely relax) IMPORTANT: Operations section typically requires the most updates as it contains implementation specifics.
-
Identify affected components from user context
Ask the user (if not already specified):
"Which components were refactored? Please specify:
- Specific files/classes that changed
- Type of change (renamed, restructured, logic changed, new components added)
- Brief description of what changed"
Alternatively, analyze recent git changes or user-specified files to identify modifications.
-
Analyze current implementation
For each affected component:
a. Read the current implementation:
- Locate the source file in the codebase
- Extract class structure, methods, annotations
- Identify relationships and dependencies
b. Compare with prompt specification:
- Find corresponding Operation/Entity/Structure section
- Note discrepancies in:
- Class names, package paths
- Method signatures and return types
- Attributes and their types
- Annotations used
- Business logic steps
- Validation rules
- Error messages
c. Categorize changes:
- Structural: Class hierarchy, dependencies, component relationships
- Behavioral: Method logic, validation rules, error handling
- Naming: Class/method/field renames
- Additions: New methods, fields, or components
- Deletions: Removed methods, fields, or components
-
Generate prompt update plan
Create a detailed update plan showing:
## Prompt Sync Plan ### Entities Section Updates - [ ] Update: ClassName - added/removed/changed fields - [ ] Update: Relationship diagram - new dependency ### Structure Section Updates - [ ] Update: Inheritance relationships - ComponentX now extends BaseY - [ ] Update: Dependencies - ServiceA now depends on ValidatorB ### Operations Section Updates - [ ] Update: "Create ClassName" operation - new method signature - [ ] Update: "Create ClassName" operation - logic steps changed - [ ] Add: New operation for NewComponent - [ ] Remove: Obsolete operation description ### Norms Section Updates - [ ] Update: New pattern adopted (e.g., Chain of Responsibility)Present this plan to the user for review before proceeding.
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.
- 4d ago First seen · 288 lines · 22 tokens per session scan A 808ccc6554b7
/spdd-sync is a command published in the GitHub repository gszhangwei/open-spdd (736 stars, last pushed 13d ago), licensed MIT. It adds 22 tokens to every session and 2,424 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.feature
Create a feature branch with sequential or timestamp numbering.
speckit.git.validate
Validate current branch follows feature branch naming conventions.