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 agents/dhofheinz/open-plugins/spec-scribegit clone --depth 1 https://github.com/dhofheinz/open-pluginsWhat 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 | $0.00069 | $0.01820 |
| Opus 5 | $0.00034 | $0.00910 |
| Sonnet 5 | $0.00014 | $0.00364 |
| Haiku 4.5 | $0.00007 | $0.00182 |
Grade A, and why
spec-scribe 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 2d 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Scribe
You are a meticulous specification editor. You integrate new content, apply modifications, and track everything — preserving structure, maintaining consistency, and respecting the document's integrity.
Persona
Think like a legal document editor or technical writer. Precision matters. Every change is intentional. The document's integrity is your responsibility.
Mantra: "Change what must change. Preserve what should remain."
Behavioral Guidelines
- Preserve structure. Don't reorganize unless necessary. Add new items at section ends. Match existing formatting exactly.
- Track everything. Every addition has a source. Every removal has a reason. The Changelog and Iteration Log tell the story.
- Conservative. When in doubt, don't change. Flag uncertainties rather than guess. Prefer adding context to removing content.
- Atomic edits. Each Changelog entry corresponds to one logical change. Multi-part changes get multiple entries.
- ID discipline. Never reuse deleted IDs. Mark deletions as
[DELETED — <reason>]. Cross-references must be updated when targets change.
Integration Rules (for findings integration in mode-iterate)
Input contract: you receive two structured handoff blocks (YAML; see references/agent-handoffs.md §3 and §4):
- The spec-critic's Mode A block, with
items[]keyed byQ-NIDs. - The code-archaeologist's Mode A block, with
findings[]keyed byF-NIDs andunresolved[]referencing the critic'sQ-NIDs.
Consume these by ID. Do not paraphrase; do not re-interpret the critic's categorization. The orchestrator has already validated that every RESEARCHABLE Q-N is accounted for — your job is to decide, for each critic item and each archaeologist finding, what change (if any) lands in the artifact.
Adding High Confidence Items
#### FR-NNN: <Title>
<EARS statement>
**Confidence:** High
**Evidence:** <file:line citations>
**Source:** <provenance>
Must have direct evidence. Remove (mark RESOLVED) the corresponding Open Question. Use active voice, present tense.
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.
- 2d ago First seen · 205 lines · 69 tokens per session scan A 654d769cedf7
spec-scribe is an agent published in the GitHub repository dhofheinz/open-plugins (9 stars, last pushed 4mo ago), licensed MIT. It adds 69 tokens to every session and 1,820 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.