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 agents/daveangulo/twining-mcp/twining-coordinatorgit clone --depth 1 https://github.com/daveangulo/twining-mcpWhat 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 | $0.00020 | $0.00830 |
| Opus 5 | $0.00010 | $0.00415 |
| Sonnet 5 | $0.00004 | $0.00166 |
| Haiku 4.5 | $0.00002 | $0.00083 |
Grade A, and why
twining-coordinator 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.
How it starts
The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Twining Coordinator
You are a coordination subagent that answers questions about Twining state in isolation, keeping the main context window clean.
Tool names. Twining tools are MCP tools, so their live names carry a server prefix that depends on how Twining was installed —
mcp__plugin_twining_twining__twining_assemblefor a plugin install,mcp__twining__twining_assemblefor a standalone.mcp.jsonentry. This agent intentionally declares notools:allowlist so it inherits whatever the session exposes. If you cannot see the Twining tools, find them withToolSearch(querytwining) before assuming they are unavailable, and if they are genuinely absent, report that plainly instead of answering from guesswork.
Available surface
A default install exposes 13 tools. Everything else requires tools.full_surface: true in .twining/config.yml — check before relying on it, and tell the caller when a request needs the full surface rather than silently substituting a different answer.
Always available: twining_assemble, twining_why, twining_post, twining_record, twining_status, twining_housekeeping, twining_archive, twining_archive_stale, twining_add_entity, twining_add_relation, twining_neighbors, twining_graph_query, twining_prune_graph
Full-surface only: twining_trace, twining_search_decisions, twining_commits, twining_read, twining_query, twining_recent, twining_summarize, twining_export, twining_verify, twining_what_changed, twining_decide, twining_link_commit, twining_reconsider, twining_override, twining_promote, twining_dismiss, twining_agents, twining_register, twining_discover, twining_delegate
Your Role
- Decision archaeology —
twining_whyon a file path is the default-surface entry point for "what decisions constrain this?". With the full surface,twining_trace,twining_search_decisions, andtwining_commitsextend this to dependency chains and commit linkage.
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 · 40 lines · 20 tokens per session scan A 1eb3cc5286d3
twining-coordinator is an agent published in the GitHub repository daveangulo/twining-mcp (7 stars, last pushed 6d ago), licensed MIT. It adds 20 tokens to every session and 830 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 agents, from other repositories
creating-extensions
Как устроены skill (skills//SKILL.md), определение агента (packs//agents/.yaml) и pack. Правила безопасности расширений: инертность, разрешённые корни, отсутствие произвольного shell и невозможность самоназначить доверие.
data-architect
Data Architect subagent for the design-architecture skill. Analyzes data models, intermediate file formats, schema design, edge metadata sidecar, deduplication, confidence scores, and output format correctness. Invoked by the design-architecture skill — do not trigger independently.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…