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-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-review)<a href="https://agentmods.dev/skills/daveangulo/twining-mcp/twining-review"><img src="https://agentmods.dev/badge/skills/daveangulo/twining-mcp/twining-review.svg" alt="Measured on agentmods" 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 | $0.00032 | $0.00533 |
| Opus 5 | $0.00016 | $0.00267 |
| Sonnet 5 | $0.00006 | $0.00107 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
twining-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 7d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Twining Review — Pre-Commit Decision Review
Review the current session's work to ensure all significant architectural and implementation decisions have been properly recorded in Twining.
Requires the full tool surface.
twining_what_changed,twining_trace,twining_search_decisions,twining_commits,twining_link_commit, andtwining_decideexist only when the project setstools.full_surface: truein.twining/config.yml. On a default install, run the equivalent review withtwining_assemble(what the next agent will see for this scope) andtwining_status(counts, warnings, open needs), then close any gap withtwining_record— passingcommit_hashfor traceability.
Workflow
1. Review What Changed
Call twining_what_changed with since set to the session start time (or the last commit time). This shows:
- New decisions made in this session
- New blackboard entries (findings, warnings, needs)
- Overridden or reconsidered decisions
2. Trace Decision Chains
For each decision made, call twining_trace with the decision ID to see:
- Upstream dependencies (decisions this one depends on)
- Downstream dependents (decisions that depend on this one)
- Verify the chain is complete — no dangling references
3. Search for Related Decisions
Call twining_search_decisions to find potentially related decisions that should be linked:
- Search by domain and scope to find nearby decisions
- Check for conflicts or superseded decisions that weren't caught
4. Verify Commit Linkage
Call twining_commits with recent commit hashes to check which decisions are already linked. For any unlinked decisions, use twining_link_commit.
5. Check Decision Coverage
Look for gaps — significant choices made during the session that aren't recorded:
- Algorithm selections
- Library/framework choices
- API design decisions
- Data model changes
- Security-relevant choices
- Performance tradeoffs
For each gap, use twining_decide to record the missing decision.
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.
- 7d ago First seen · 58 lines · 32 tokens per session scan A cbebe3d84a18
twining-review is a skill published in the GitHub repository daveangulo/twining-mcp (7 stars, last pushed 12d ago), licensed MIT. It adds 32 tokens to every session and 533 once invoked, about $0.0002 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
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
understand-diff
Use when you need to analyze git diffs or pull requests to understand what changed, affected components, and risks.
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
github-automation
GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.