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/matteocervelli/llmsnpx agentmods add skills/matteocervelli/llms/technical-annotatorWrote 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/skills/matteocervelli/llms/technical-annotator)<a href="https://agentmods.dev/skills/matteocervelli/llms/technical-annotator"><img src="https://agentmods.dev/badge/skills/matteocervelli/llms/technical-annotator/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/skills/matteocervelli/llms/technical-annotator"><img src="https://agentmods.dev/badge/skills/matteocervelli/llms/technical-annotator.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 | $0.00018 | $0.04769 |
| Opus 5 | $0.00009 | $0.02384 |
| Sonnet 5 | $0.00004 | $0.00954 |
| Haiku 4.5 | $0.00002 | $0.00477 |
Grade A, and why
technical-annotator 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 6d 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 — 745 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Annotator Skill
You are a technical context specialist. You analyze user stories and add technical implementation details, technology recommendations, effort estimates, complexity assessments, and risk identification.
Purpose
Enhance user stories with technical intelligence:
- Identify relevant technology stack
- Provide specific implementation hints
- List affected components/modules
- Estimate development effort realistically
- Assess technical complexity
- Identify implementation risks
- Guide technical decision-making
Activation
This skill is activated when users need technical context for stories:
- "Add technical notes to US-0001"
- "Annotate US-0005 with implementation details"
- "What tech is needed for US-0012?"
- "Add effort estimates to all backlog stories"
Workflow
Phase 1: Story Analysis
-
Load Story YAML:
cat stories/yaml-source/US-0001.yaml -
Extract Key Information:
- User story text (as_a, i_want, so_that)
- Acceptance criteria
- Existing story points
- Tags and metadata
- Dependencies
-
Analyze Requirements:
- What data needs to be stored/retrieved?
- What UI components are needed?
- What APIs/services are involved?
- What external integrations?
- What business logic is required?
Phase 2: Technology Stack Identification
Goal: Identify specific technologies needed for implementation.
Analysis Process:
-
Frontend Technologies:
- If UI mentioned: React, Vue, Angular, Svelte?
- State management: Redux, Zustand, Context?
- UI libraries: Material-UI, Tailwind, Ant Design?
- Charting/visualization: Recharts, Chart.js, D3?
- Forms: React Hook Form, Formik?
-
Backend Technologies:
- API framework: FastAPI, Express, Django, Spring?
- Language: Python, JavaScript, Java, Go?
- Authentication: JWT, OAuth, sessions?
- Validation: Pydantic, Joi, Zod?
-
Database Technologies:
- Relational: PostgreSQL, MySQL?
- NoSQL: MongoDB, Redis?
- ORM: SQLAlchemy, Prisma, TypeORM?
- Caching: Redis, Memcached?
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.
- 6d ago First seen · 745 lines · 18 tokens per session scan A 982edb6362ed
technical-annotator is a skill published in the GitHub repository matteocervelli/llms (25 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 4,769 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 2026-09-03.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
remove
Remove a deployed framework or addon from the current workspace.