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/ripemangobox/bite/code-context-paper-retrievalnpx skills add RipeMangoBox/BITE --skill code-context-paper-retrievalgit clone --depth 1 https://github.com/RipeMangoBox/BITEWhat 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 | $0.00108 | $0.01219 |
| Opus 5 | $0.00054 | $0.00609 |
| Sonnet 5 | $0.00022 | $0.00244 |
| Haiku 4.5 | $0.00011 | $0.00122 |
Grade A, and why
code-context-paper-retrieval 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 3d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Context Paper Retrieval
This skill is a compatibility alias for papers-query-knowledge-base in
mode: code-context. Prefer that query mode for new routing and keep this
skill for older prompts that call it by name.
What this skill does
For code implementation/refactor/planning tasks, this skill provides the most relevant paper evidence from the local knowledge base for the current code context.
Fixed retrieval order:
obsidian-vault/analysis/(primary retrieval and evidence layer)obsidian-vault/paperPDFs/(recommend deeper reading only when necessary)obsidian-vault/index/(useindex.jsonlfor fast filtering when present; otherwise reference the Markdown pages only when statistics, overview pages, Obsidian jumps, or backlink support are needed)
Two output levels:
brief: 3-5 must-read papers + analysis note path + whether PDF reading is recommendeddeep: broader candidate list + comparison rationale + practical implementation suggestions
Environment Detection (must be completed before execution)
Before running any script, the Python environment must be confirmed. Check in this priority order:
- Environment files in the target codebase (high to low):
environment/environment.yml/environment.yaml(conda)environment/requirements.txt/requirements*.txtenvironment/pyproject.toml(check[project.dependencies]or[tool.poetry.dependencies])setup.py/setup.cfg
- Infer conda env name from environment files: read
name:inenvironment/environment.ymland check whether that env exists (conda env list). - If none found or still uncertain: proactively ask the user, stating no environment file was found, and request one of:
- conda environment name, or
- Python interpreter path, or
- confirmation to use system default Python
Prohibited behavior: do not guess and run scripts with python3/python before environment confirmation.
Triggering
Core principle: retrieve before code changes, not after
What ships with it
2 files 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.
- 3d ago First seen · 120 lines · 108 tokens per session scan A 32a60b501be8
code-context-paper-retrieval is a skill published in the GitHub repository RipeMangoBox/BITE (60 stars, last pushed 20d ago), licensed MIT. It adds 108 tokens to every session and 1,219 once invoked, about $0.0005 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 skills, from other repositories
compile-wiki
Merge source summaries into durable concept pages with backlinks, index entries, and explicit open questions.
ingest-sources
Review newly ingested raw sources and draft or update source summary notes in notes/Sources/.
qa-agent
Answer questions from the vault, then file durable insights back into the knowledge base.
research-workflow
Manage resumable research runs under research/ and coordinate the collect, review, report, import, and archive steps.
lint-heal
Scan the vault for contradictions, unsupported claims, structural weaknesses, and missing pages, then repair what is safe.
render-output
Convert vault content into downstream outputs like memos, reports, slide outlines, diagrams, and plot specifications.