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 daveangulo/twining-mcp --skill twining-semantic-reviewgit clone --depth 1 https://github.com/daveangulo/twining-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/daveangulo/twining-mcp/twining-semantic-review)<a href="https://agentmods.dev/skills/daveangulo/twining-mcp/twining-semantic-review"><img src="https://agentmods.dev/badge/skills/daveangulo/twining-mcp/twining-semantic-review/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/daveangulo/twining-mcp/twining-semantic-review"><img src="https://agentmods.dev/badge/skills/daveangulo/twining-mcp/twining-semantic-review.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 | $0.00077 | $0.01168 |
| Opus 5 | $0.00039 | $0.00584 |
| Sonnet 5 | $0.00015 | $0.00234 |
| Haiku 4.5 | $0.00008 | $0.00117 |
Grade A, and why
twining-semantic-review 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 9d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Twining Semantic Review — LLM-Judged Staleness
Deterministic staleness (twining_housekeeping with staleness_review: true) catches
orphans-by-structure: the scope path is gone, affected files deleted, branch removed.
It cannot catch entries that are structurally intact but reference concepts the
project has moved past — "Wave 3 review action items", "HMS Lancaster compliance",
a sprint that closed a year ago. A future agent finding those will go looking for
concepts that don't exist and hallucinate explanations.
This skill puts the judging model — you — in that loop. You are the LLM; no API key, no server-side model call, no cost beyond this session. Nothing is archived without explicit user confirmation.
When to Invoke
- The user asks for a semantic review, deep cleanup, or "are any of these entries still relevant?"
- After a milestone/version ships and its planning vocabulary is retired
- Deterministic housekeeping reports clean but
twining_statusshows a large, old entry population
Never run this as a side effect of another task. It is opt-in by design.
Workflow
1. Ground yourself in what is CURRENT
Before judging anything, build the "still alive" picture:
git branch --listand the current branch — active lines of workREADME.md/ project docs headline — what the project is nowtwining_status— entry counts, current phase if tracked- The 10 most recent blackboard entries — today's working vocabulary
2. Load review candidates
- Decisions:
twining_whyon the major scopes (e.g.src/,plugin/), includinginclude_superseded: false(superseded ones are already retired). Use themoretier andidsdrill-down for full rationale where needed. - Blackboard entries:
twining_readwith no type filter, oldest first if the surface allows.twining_readrequirestools.full_surface: true— in lite mode, review decisions only (viatwining_why) plus thedangling_warningsitems fromtwining_housekeeping.
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.
- 9d ago First seen · 95 lines · 77 tokens per session scan A ae081ea481a2
twining-semantic-review is a skill published in the GitHub repository daveangulo/twining-mcp (7 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 1,168 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 2026-08-31.
Other skills, from other repositories
shodh-memory
Persistent memory system for AI agents. Use this skill to remember context across conversations, recall relevant information, and build long-term knowledge. Activate when you need to store decisions, learnings, errors, or context that should persist beyond the current session.
lemmalog
Externalize working memory and logical state into the lemmalog Datalog engine (MCP). Use for ANY multi-step task where state should outlive one context window or span agents: long investigations, debugging sessions, audits, multi-agent searches, systematic explorations, planning with many interdependent constraints…
braindb-agent
Persistent memory across sessions via the BrainDB agent. Use at conversation start and whenever you need to recall what you know about the user or save new information to long-term memory.
autograph
Schema-as-code enforcement for any Obsidian vault. Zero hardcoded domains. Use when creating vault cards, checking vault health, running schema compliance, deduplicating entities, generating MOC indexes, running decay cycles, bootstrapping a vault, fixing wikilinks, finding orphans or backlinks, extracting entities…
dbrain-processor
Personal assistant for processing daily voice/text entries from Telegram. Classifies content, saves thoughts to Obsidian with wiki-links, generates HTML reports. Integrates Your Business context (clients, projects, CRM). Triggers on /process command or daily 21:00 cron.
ori-memory
Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.