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 commands/josefslerka/study-kit/researchgit clone --depth 1 https://github.com/josefslerka/study-kitWhat 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 | $0.00019 | $0.00396 |
| Opus 5 | $0.00010 | $0.00198 |
| Sonnet 5 | $0.00004 | $0.00079 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
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 2d 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.
What it actually says
Run the secondary-literature ingest per CLAUDE.md, section "Secondary literature".
For a new file in raw_secondary/:
- Read it and compile its POSITION (what it claims about the subject of the study) — by
PARAPHRASE, with provenance
(raw_secondary/<file>)and an anchor phrase for each key claim. Do NOT cite it as a fact about the world, only as someone's position with attribution. - Two-layer verification (rule 1): for each attributed position verify not only that the anchor phrase IS in the file, but that the position holds in CONTEXT — that the use does not distort what the author actually claims. Word-match is not enough; distorting a position is fabrication. Uncertain context → weaken or drop.
- Place it in
process/research.md. Map agreements and divergences with positions already there. - Mark the gap the study's thesis fills (what this literature overlooks).
- Recompute originality: what of the thesis does this source already say itself → what remains as the author's own contribution? Write that remainder. (A source that confirms the thesis can quietly take its novelty.)
- Type and balance: is it a theoretical lens, or a document of field consensus? When a 3rd+ theoretical lens accrues without a single field source, REPORT the imbalance (risk of an "apparatus parade") — what's missing is scholarship about the subject, not another lens.
- Attribute ONLY what you find in the file — never "the author would probably say". Don't name a
source outside
raw_secondary/at all.
Log it. After a few sources, offer to write the positioning for the introduction from
research.md.
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.
- 2d ago First seen · 27 lines · 19 tokens per session scan A 72f781a0b4db
research is a command published in the GitHub repository josefslerka/study-kit (5 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 396 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.