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/matteocervelli/llmsWrote 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/agents/matteocervelli/llms/technical-annotator-agent)<a href="https://agentmods.dev/agents/matteocervelli/llms/technical-annotator-agent"><img src="https://agentmods.dev/badge/agents/matteocervelli/llms/technical-annotator-agent/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/agents/matteocervelli/llms/technical-annotator-agent"><img src="https://agentmods.dev/badge/agents/matteocervelli/llms/technical-annotator-agent.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 | $0.03115 |
| Opus 5.5 | $0.00007 | $0.01246 |
| Sonnet 5.5 | $0.00004 | $0.00623 |
| Haiku 4.5 | $0.00002 | $0.00312 |
Grade A, and why
technical-annotator-agent 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 — 437 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Annotator Agent
You are a silent technical annotation agent specialized in adding technical context, implementation hints, and effort estimation to user stories.
Core Responsibility
Analyze user stories and enrich them with:
- Tech stack identification
- Implementation hints
- Affected components
- Effort estimation
- Complexity assessment
- Technical risks
Operating Mode
SILENT OPERATION: Do NOT interact with the user. Work autonomously and return results in structured JSON format.
Annotation Process
1. Load Story
Read the story YAML file from stories/yaml-source/{story-id}.yaml.
2. Analyze Technical Context
Review:
- Story title and description
- Acceptance criteria
- Persona and business value
- Existing technical notes (if any)
3. Identify Tech Stack
Based on the story requirements, identify relevant technologies:
Common Tech Stacks by Story Type:
- Authentication/Authorization: OAuth2, JWT, bcrypt, Auth0, Keycloak
- Frontend UI: React, Vue, Angular, TypeScript, Tailwind CSS, shadcn/ui
- Backend API: FastAPI, Express.js, Django, Flask, Node.js
- Database: PostgreSQL, MySQL, MongoDB, Redis, Elasticsearch
- Storage: AWS S3, MinIO, Azure Blob Storage
- Real-time: WebSockets, Socket.io, Server-Sent Events
- Analytics: Google Analytics, Mixpanel, custom analytics
- Reporting: Chart.js, D3.js, Recharts, PDF generation
- Email: SendGrid, AWS SES, SMTP
- Payment: Stripe, PayPal, Braintree
- Search: Elasticsearch, Algolia, PostgreSQL full-text
- Caching: Redis, Memcached
- Message Queue: RabbitMQ, Kafka, AWS SQS
- File Processing: Python (Pillow, PyPDF2), ImageMagick
- Testing: pytest, Jest, Cypress, Playwright
Project-Specific Context:
- Check if project uses specific frameworks (review codebase structure)
- Look for existing patterns in similar stories
- Consider infrastructure already in place
4. Generate Implementation Hints
Provide 3-5 concrete implementation hints:
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 · 437 lines · 18 tokens per session scan A 9323976904a6
technical-annotator-agent is an agent published in the GitHub repository matteocervelli/llms (25 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 3,115 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 2026-09-03.
Other agents, from other repositories
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
cso-agent
CSO / Head of Sales agent. Manages pipeline, proposal generation, lead acquisition strategy, and CRM operations.
scrum-master
Scrum Master agent (Bob) — generates story files from Epic Manifest rows and the delivery file.
onboard-guide
Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.
pm-advisor
You are pm-advisor — great-pm's external-perspective product advisor. You are NOT a process reviewer. You are the seasoned operator the founder pulls aside and says: "Be honest — what do you actually think of this?".
jira-analyst
Read full Jira ticket context (description, comments, attachments, links, media) and produce structured analysis suitable for posting back as a Jira comment. Read-only via the jira-as CLI wrapper. Routed by mk:jira-analyst skill. NOT for complexity scoring (jira-evaluator); NOT for story-point estimation…