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 Lianye-Scythe/scythe-context-mcp --skill scythe-contextgit clone --depth 1 https://github.com/Lianye-Scythe/scythe-context-mcpWrote 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/lianye-scythe/scythe-context-mcp/scythe-context)<a href="https://agentmods.dev/skills/lianye-scythe/scythe-context-mcp/scythe-context"><img src="https://agentmods.dev/badge/skills/lianye-scythe/scythe-context-mcp/scythe-context/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lianye-scythe/scythe-context-mcp/scythe-context"><img src="https://agentmods.dev/badge/skills/lianye-scythe/scythe-context-mcp/scythe-context.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00043 | $0.01623 |
| Opus 5.5 | $0.00017 | $0.00649 |
| Sonnet 5.5 | $0.00009 | $0.00325 |
| Haiku 4.5 | $0.00004 | $0.00162 |
Grade A, and why
scythe-context 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 today.
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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scythe Context CLI
Use the installed scythe-context command. Check --version when newly documented fields or behavior are missing. Read scythe-context --help when additional options are needed. If unavailable, use a built source checkout through node /absolute/path/to/scythe-context-mcp/dist/command.js; do not download or install packages just to discover commands.
Choose the lookup tool
- Read files directly when the relevant path and range are known. Use
rg --filesto locate a known filename or path pattern. - Use
rgfor exact names, error messages, literals, regular expressions, or an exhaustive textual match list. It searches current files without an index; prefer it for a simple lookup rather than building an index solely for that lookup. - Use Scythe
searchwhen you need ranked candidates across an unfamiliar repository. Usecontextwhen import relationships and bounded related snippets would help trace the implementation; userelatedfor a focused view of an indexed file's symbols, imports, and reverse imports. - Local
keywordretrieval depends on matching terms; it does not provide semantic understanding or reliably bridge different languages or synonyms. Start with identifiers or technical terms likely to appear in the source. If wording mismatch prevents useful results, consider the optional embeddings workflow below when within scope. - Once results identify enough relevant code, read those file ranges and continue the task. Avoid repeating the same lookup through both tools without a missing piece to resolve. Neither faster task completion nor lower total token use is guaranteed.
Local lookup
Run commands in the target repository or supply --project /absolute/repo/path. Explicit project selection overrides the configured default.
scythe-context status
# Only when metadata is missing or stale:
scythe-context index
scythe-context context "auth token validation"
Search and context commands default to local keyword mode and paths output. Index freshness affects these results; rg and direct reads use current file contents. Read the matching file ranges next.
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.
- today First seen · 81 lines · 43 tokens per session scan A c8ca7a8a2a1a
scythe-context is a skill published in the GitHub repository Lianye-Scythe/scythe-context-mcp (2 stars, last pushed today), licensed Apache-2.0. It adds 43 tokens to every session and 1,623 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-18.
Other skills, from other repositories
graph-retrieval
Exposes graph-based retrieval as a tool capability via querygraph. Reads normalized graph store files, builds a query-relevant subgraph, and returns LLM-friendly semantic triples with replayable evidence metadata.
knowledge-layer
High-level deployment wrapper over RepoBrain core with graph-first knowledge injection and all-file support. Exposes refreshfilesystem and askfilesystem for building and querying the knowledge graph.
agent-repo-init
Bootstraps a new multi-agent repository from the RepoBrain template via initagentrepo. Supports quick scaffold and full runtime profile setup including MCP toggle, swarm preference, sandbox type, and optional git init. LLM configuration is handled later by rb-setup.
research
Performs deep research on a topic via deepresearch. Simulates a multi-step research process and returns a comprehensive research result as a string.
search
Deep research powered by Exa. Use for lead generation, literature reviews, deep dives, competitive analysis, or any query where one search falls short, including phrases like 'research this', 'find everything about', 'find me all', or 'deep dive on'.
Exa Agent
Use Exa Agent for multi-step web research, list-building, enrichment, structured output, run continuation, and coverage validation. Exa Agent can access additional data providers: fiber, financialdatasets, similarweb, baselayer, affiliate, particle, and jinko.