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 skills add AI-4-Phi/PhilLit --skill philosophy-researchgit clone --depth 1 https://github.com/AI-4-Phi/PhilLitWrote 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/ai-4-phi/phillit/philosophy-research)<a href="https://agentmods.dev/skills/ai-4-phi/phillit/philosophy-research"><img src="https://agentmods.dev/badge/skills/ai-4-phi/phillit/philosophy-research.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00078 | $0.03232 |
| Opus 5 | $0.00039 | $0.01616 |
| Sonnet 5 | $0.00016 | $0.00646 |
| Haiku 4.5 | $0.00008 | $0.00323 |
Grade A, and why
philosophy-research 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 8d 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 — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Philosophy Research Skill
Search and retrieve academic philosophy literature using structured APIs instead of WebSearch.
Setup check: If the current directory has no .phillit/ marker, PhilLit has not been set up here — offer to run /phillit:setup (a quick one-time step) before continuing.
When to Use This Skill
Use this skill when:
- Searching for philosophy papers, articles, or concepts
- Accessing SEP (Stanford Encyclopedia of Philosophy) content
- Finding citations and references for papers
- Verifying that a paper exists with correct metadata
- Building bibliographies for literature reviews
Search Workflow
Batching: when you have several searches, run them in ONE shell call —
&+waitbetween scripts hitting DIFFERENT APIs, plain sequential lines between calls to the SAME API (its shared rate limiter would serialize them anyway, and the limiter's file lock is Unix-only, so same-API parallelism buys nothing and can race on Windows). Parallel fan-outs give each script--outputand finish withgrep -m1 '"status"' <files>— full results land in files, one short attributed status line each lands on screen; sequential same-API chains with small payloads skip both and just consume the inline stdout (exception:verify_paper.pyalways keeps--output— the metadata cleaner reads its files — while its status prints inline). Never batch across a dependency: a search whose query is composed from an earlier search's results is its own call.
Phase 1: SEP & IEP (Most Authoritative)
# Discover relevant SEP articles
bash "$PHILLIT_ROOT/bin/phillit-run" skills/philosophy-research/scripts/search_sep.py "free will"
# Extract structured content from an SEP entry
bash "$PHILLIT_ROOT/bin/phillit-run" skills/philosophy-research/scripts/fetch_sep.py freewill --sections "preamble,1,2,bibliography"
bash "$PHILLIT_ROOT/bin/phillit-run" skills/philosophy-research/scripts/fetch_sep.py freewill --bibliography-only
# Discover relevant IEP articles (different coverage from SEP)
bash "$PHILLIT_ROOT/bin/phillit-run" skills/philosophy-research/scripts/search_iep.py "free will"
# Extract structured content from an IEP entry
bash "$PHILLIT_ROOT/bin/phillit-run" skills/philosophy-research/scripts/fetch_iep.py freewill --sections "1,2,3,bibliography"
bash "$PHILLIT_ROOT/bin/phillit-run" skills/philosophy-research/scripts/fetch_iep.py freewill --bibliography-only
What ships with it
27 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.
- scripts/__init__.py 843 B runs code
- scripts/brave_search.py 8.1 KB runs code
- scripts/check_setup.py 16 KB runs code
- scripts/citation_context.py 6.2 KB runs code
- scripts/fetch_iep.py 12 KB runs code
- scripts/fetch_ndpr.py 8.3 KB runs code
- scripts/fetch_sep.py 18 KB runs code
- scripts/fetch_web.py 13 KB runs code
- scripts/get_abstract.py 22 KB runs code
- scripts/get_iep_context.py 4.5 KB runs code
- scripts/get_sep_context.py 4.6 KB runs code
- scripts/output.py 7.9 KB runs code
- scripts/rate_limiter.py 18 KB runs code
- scripts/s2_batch.py 10 KB runs code
- scripts/s2_citations.py 13 KB runs code
- scripts/s2_formatters.py 3.4 KB runs code
- scripts/s2_recommend.py 13 KB runs code
- scripts/s2_search.py 16 KB runs code
- scripts/search_arxiv.py 7.2 KB runs code
- scripts/search_cache.py 6.1 KB runs code
- scripts/search_core.py 15 KB runs code
- scripts/search_iep.py 3.6 KB runs code
- scripts/search_ndpr.py 10 KB runs code
- scripts/search_openalex.py 20 KB runs code
- scripts/search_philpapers.py 3.8 KB runs code
- scripts/search_sep.py 3.6 KB runs code
- scripts/verify_paper.py 36 KB runs code
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.
- 8d ago First seen · 268 lines · 78 tokens per session scan A 7d6b9968da9c
philosophy-research is a skill published in the GitHub repository AI-4-Phi/PhilLit (42 stars, last pushed 3d ago), licensed Apache-2.0. It adds 78 tokens to every session and 3,232 once invoked, about $0.0004 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
rational-buddhism
A way to examine spiritual, supernatural, or other difficult-to-test claims using skepticism, personal testing, and scientific standards.
life-meaning
A guide for reflecting on personal purpose, effort, suffering, and mortality when life feels empty or directionless.
roundtable
A guided discussion format in which a moderator brings several real people’s documented viewpoints into a structured debate about one topic.
academic-paper-composer
Systematic writing framework for philosophy and interdisciplinary academic papers from optimized outline to submission-ready manuscript. Use when users want to: (1) write a paper from a detailed outline, (2) ensure quality control during writing, (3) maintain consistency across chapters, (4) prepare a submission-ready…
academic-paper-strategist
Systematic strategic planning framework for philosophy and interdisciplinary academic papers targeting preprint platforms (PhilArchive, arXiv, PhilSci-Archive). Use when users want to: (1) plan a paper on a specific topic, (2) identify research gaps and assess originality, (3) develop optimized paper outlines, (4)…
worldview-synthesis
This skill should be used when someone wants to articulate, explore, or document their personal worldview, values, or philosophy. Triggers on "articulate my values", "figure out what I believe", "document my philosophy", "write a manifesto", "define my leadership philosophy", "explore my beliefs". Surfaces beliefs…