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 skills/tony/skills/scholar-annotatenpx skills add tony/skills --skill scholar-annotategit clone --depth 1 https://github.com/tony/skillsWrote 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/tony/skills/scholar-annotate)<a href="https://agentmods.dev/skills/tony/skills/scholar-annotate"><img src="https://agentmods.dev/badge/skills/tony/skills/scholar-annotate.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 5.1 | $0.00029 | $0.00966 |
| Opus 5 | $0.00015 | $0.00483 |
| Sonnet 5 | $0.00006 | $0.00193 |
| Haiku 4.5 | $0.00003 | $0.00097 |
Grade A, and why
scholar-annotate 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
this skill
The prose path. Without it, a written corpus enters the pipeline as unstructured text and its citations degrade to "somewhere in chapter 3".
Read references/citation.md for the locator rules this stage
implements.
User arguments: $ARGUMENTS
Locator precedence
Take the most stable locator the source actually supports. In order:
A pinned line anchor — where the source is a text file in version control.
Most stable, and verify can check it mechanically.
Chapter and section — where the work is structured. Survives repagination and translation between print and digital.
Page — only where sources.jsonl records the edition. A page number
without an edition is not a locator; it is a number that happens to be true of
one printing.
A search string — where the source has no stable anchor at all: a PDF
without pagination, an audio transcript, a scanned document. Quote enough
unique text to be found by search, and record in sources.jsonl that this
source's locator is a search string rather than a position, so verify checks
it by search rather than by position.
Never invent a position the source does not have. A confident wrong locator costs a reader more than an honest search string.
Procedure
1. Confirm the edition
Read the source's row in sources.jsonl. If the locator scheme is page and
the edition is unrecorded, stop and record the edition first.
2. Extract quotations
One quotation per concept the author names, long enough to stand on its own when read out of context. A quotation that only makes sense beside the sentence before it is too short.
3. Attach margin notes
The note says what the quotation is evidence for — which is the analyst's
judgement and must stay visibly separate from the author's words. Never blend
the two into a paraphrase; extract needs to know which is which.
4. Write the quotation set
{"source": "<source id from sources.jsonl>", "locator": "ch.3 §2", "quote": "...", "note": "the author's own term for the boundary"}
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 101 lines · 29 tokens per session scan A 164d53f32cf8
scholar-annotate is a skill published in the GitHub repository tony/skills (2 stars, last pushed 8d ago), licensed MIT. It adds 29 tokens to every session and 966 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 2026-08-31.
Other skills, from other repositories
postgres-database-migration
Use this skill for planning, testing, and safely executing PostgreSQL schema migrations — especially when working with production data or shared databases. Trigger when user asks to: Test a schema migration before applying it to production Add, remove, or rename columns safely on a live table Change a column's data…
design-postgis-tables
Comprehensive PostGIS spatial table design reference covering geometry types, coordinate systems, spatial indexing, and performance patterns for location-based applications.
setup-timescaledb-hypertables
Use this skill when creating database schemas or tables for Timescale, TimescaleDB, TigerData, or Tiger Cloud, especially for time-series, IoT, metrics, events, or log data. Use this to improve the performance of any insert-heavy table. Trigger when user asks to: Create or design SQL schemas/tables AND…
migrate-postgres-tables-to-hypertables
Use this skill to migrate identified PostgreSQL tables to Timescale/TimescaleDB hypertables with optimal configuration and validation. Trigger when user asks to: Migrate or convert PostgreSQL tables to hypertables Execute hypertable migration with minimal downtime Plan blue-green migration for large tables Validate…
pgvector-semantic-search
Use this skill for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search. Trigger when user asks to: Store or search vector embeddings in PostgreSQL Set up semantic search, similarity search, or nearest neighbor search Create HNSW or IVFFlat indexes for vectors…
postgres-hybrid-text-search
Use this skill to implement hybrid search combining BM25 keyword search with semantic vector search using Reciprocal Rank Fusion (RRF). Trigger when user asks to: Combine keyword and semantic search Implement hybrid search or multi-modal retrieval Use BM25/pgtextsearch with pgvector together Implement RRF (Reciprocal…