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/dromara/liteflow/researchnpx skills add dromara/liteflow --skill researchgit clone --depth 1 https://github.com/dromara/liteflowWhat 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 | $0.00011 | $0.00032 |
| Opus 5 | $0.00005 | $0.00016 |
| Sonnet 5 | $0.00002 | $0.00006 |
| Haiku 4.5 | $0.00001 | $0.00003 |
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
Research Skill
Use this skill when the request requires research planning.
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 · 9 lines · 11 tokens per session scan A 45d2cf1d3405
research is a skill published in the GitHub repository dromara/liteflow (3,842 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 11 tokens to every session and 32 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 2026-08-30.
Other skills, from other repositories
add-guarantee
Add a new runtime guarantee, safety property, or feature to Blaze the theorem-with-test way — attacking concurrent test first, then implementation, then the README claims table. Use whenever the user asks to add, harden, or make safe any runtime behavior (limits, isolation, EditClass semantics, metrics, canary policy…
grow-language
Add a language feature to Blaze — a token, operator, statement, control-flow form, or type — through the full seven-station pipeline with the diagnostics gate kept in lockstep with the lowerer. Use whenever the user asks for new syntax or semantics ("add strings", "support for-loops", "a modulo operator", "explicit…
bench-and-readme
Run Blaze's benchmark suite (reload latency, call throughput, interpreter comparison, canary overhead) and update every performance number in the README honestly and machine-labeled. Use when the user asks about performance, "how fast is it", re-measuring, updating benchmark or README numbers, preparing…
verify
Run Blaze's full green gate — workspace tests, clippy, and the asserted demo stories — and triage any failure by subsystem. Use before every commit, after any change under blaze-/src, tests, or examples, whenever the user asks "is it green", "run the tests", "check everything", and at the end of any task that touched…
mps-console
Use when running or generating MPS Console code, or when writing jetbrains.mps.lang.smodel.query queries anywhere in MPS (intentions, behavior, actions, generator queries, plain BaseLanguage). Covers the console command languages (jetbrains.mps.console.base / ideCommands / internalCommands / scripts): BLCommand /…
mps-distribution-build
Use when bundling a new plain Java/Kotlin plugin into MPS distribution archives, debugging packaging/layout issues in build/mps.xml, tracing where per-plugin artefacts end up, or editing plugins/mps-build/solutions/mpsBuild/models/build.mps (the source of truth that generates every build/mps.xml). The skill covers the…