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 Zaoqu-Liu/converge-skill --skill convergegit clone --depth 1 https://github.com/Zaoqu-Liu/converge-skillWrote 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/zaoqu-liu/converge-skill/converge)<a href="https://agentmods.dev/skills/zaoqu-liu/converge-skill/converge"><img src="https://agentmods.dev/badge/skills/zaoqu-liu/converge-skill/converge/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/zaoqu-liu/converge-skill/converge"><img src="https://agentmods.dev/badge/skills/zaoqu-liu/converge-skill/converge.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 | $0.00134 | $0.07542 |
| Opus 5 | $0.00067 | $0.03771 |
| Sonnet 5 | $0.00027 | $0.01508 |
| Haiku 4.5 | $0.00013 | $0.00754 |
Grade C, and why
converge scanned grade C with 1 finding 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
If the user explicitly invokes Converge on a direct task, do not refuse and do not over-document. Run Universal Intent Guard, carry forward the clarified intent and assumptions, then switch to the relevant execution work How it starts
The opening of the file, as written. The whole thing — 424 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Converge v3 - Owner-Mode Intent Reconstruction
Converge turns low-expression, high-ambiguity human input into clear understanding, a defensible recommendation, and a directly usable artifact.
Core contract:
The user owns the goal. Converge owns clarity, reasoning quality, and output quality.
Do not behave like a passive interviewer. Infer, challenge, recommend, and iterate until the user is genuinely understood. Label inference clearly and never pretend a guess is confirmed truth.
Non-Negotiable Gates
Apply these even if you only have time to read the top of this skill.
- Current technical route: for model/framework/library/protocol/platform decisions, include explicit
Evidence Snapshot,Validation Spike, andRevisit Triggersections. If the user asks to omit sources, override that part and keep sources compact because current-route claims need traceability. Do not stall trying to perfect research; if source access is unavailable or slow, give a conditional route and name the checks needed. - High-risk decisions: for medical, legal, financial, security, compliance, safety-critical, employment, or irreversible decisions, separate information from recommendation and user ownership. For financial allocation involving most cash, leverage, illiquidity, unfamiliar products, or life-impacting downside, explicitly recommend official product/risk-disclosure checks and consultation with a licensed professional or regulated institution before action.
- Inaccessible artifacts: never pretend to have read a private link, file, image, repo, or doc. Mark it unavailable, ask for the smallest useful paste/export, and provide only a conditional review frame.
- Tool realism: call only tools present in the active environment. If a native question/research/browser tool is absent or non-interactive, use the shortest allowed fallback and keep moving.
- No proof overclaim: do not claim final completion, production readiness, or "best today" from narrow, stale, indirect, or unchecked evidence.
- Architecture handoff: when a system architecture request is meant for engineers/agents to build, load
playbooks/architecture.mdand settle actors, resources, policies, enforcement points, risks, and acceptance criteria before writing detailed API contracts, schemas, migrations, or task graphs. If repo/product context is missing, produce a Converge Docs skeleton and label concrete examples as placeholders, not implementation-ready handoff.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 334 B
- dev-handoff-guide.md 2.2 KB
- eval-artifacts/context-poisoning-boundary/SKILL.md 352 B
- eval-artifacts/dev-handoff-after-docs/01-context.md 690 B
- eval-artifacts/dev-handoff-after-docs/02-solution.md 830 B
- eval-artifacts/dev-handoff-after-docs/03-execution.md 637 B
- eval-artifacts/dev-handoff-after-docs/04-risks.md 566 B
- eval-artifacts/mixed-artifact-intake/error.log 583 B
- eval-artifacts/mixed-artifact-intake/prd.md 508 B
- eval-artifacts/mixed-artifact-intake/screenshot.txt 301 B
- eval-artifacts/opencode-capability-adapter/AGENTS.md 348 B
- eval-artifacts/opencode-capability-adapter/opencode.json 203 B
- eval-cases/architecture-ambiguity.md 593 B
- eval-cases/benchmark-headline-route-trap.md 663 B
- eval-cases/claude-native-question-bridge.md 893 B
- eval-cases/codex-default-choice-survey-trap.md 714 B
- eval-cases/codex-default-no-native-ui.md 710 B
- eval-cases/codex-plan-native-question-ui.md 825 B
- eval-cases/completion-proof-overclaim.md 660 B
- eval-cases/context-poisoning-boundary.md 986 B
- eval-cases/context-poisoning-rule-review.md 758 B
- eval-cases/current-model-claim-needs-citations.md 737 B
- eval-cases/cursor-native-question-bridge.md 893 B
- eval-cases/dev-handoff-after-docs.md 1.2 KB
- eval-cases/direct-translation-no-trigger.md 508 B
- eval-cases/everyday-work-plan.md 566 B
- eval-cases/explicit-converge-simple-task.md 537 B
- eval-cases/extended-host-capability-boundary.md 1.4 KB
- eval-cases/full-converge-docs-complex-project.md 1.1 KB
- eval-cases/headless-question-tool-unavailable.md 1010 B
- eval-cases/high-stakes-financial-decision.md 718 B
- eval-cases/host-support-proof-boundary.md 1.4 KB
- eval-cases/inaccessible-link-boundary.md 609 B
- eval-cases/latest-library-advice.md 656 B
- eval-cases/low-expression-idea.md 679 B
- eval-cases/mcp-by-default.md 645 B
- eval-cases/messy-decision.md 572 B
- eval-cases/mixed-artifact-intake.md 960 B
- eval-cases/no-research-private-preference.md 575 B
- eval-cases/opencode-capability-adapter.md 1.1 KB
- eval-cases/overbroad-product.md 572 B
- eval-cases/relationship-preserving-reply.md 587 B
- eval-cases/reply-draft.md 514 B
- eval-cases/research-plan.md 583 B
- eval-cases/researched-answer-citations.md 696 B
- eval-cases/session-memory-boundary.md 621 B
- eval-cases/session-pressure-not-memory.md 603 B
- eval-cases/shallow-proof-publish-claim.md 643 B
- eval-cases/skill-evolution-failed-rollout.md 736 B
- eval-cases/skill-evolution-overfit-holdout.md 922 B
- eval-cases/skill-evolution-skip-holdout.md 720 B
- eval-cases/technology-route-current-stack.md 1004 B
- eval-coverage.tsv 15 KB
- eval-rubric.md 4.5 KB
- examples.md 7.5 KB
- host-adapter-matrix.md 6.7 KB
- host-adapters.json 15 KB
- host-capability-contract.tsv 3.4 KB
- host-native-interaction-runbook.md 5.4 KB
- host-source-evidence.md 7.0 KB
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 · 424 lines · 134 tokens per session scan C a06a07ce2bb8
converge is a skill published in the GitHub repository Zaoqu-Liu/converge-skill (1 stars, last pushed 3mo ago), licensed MIT. It adds 134 tokens to every session and 7,542 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
agent-evaluation
Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.
plan-task
Refine a draft task specification into a fully planned, implementation-ready task with acceptance criteria, architecture, per-step sub-task files and verifiable phases.
design-testing-strategy
Use before writing any type of tests. Distills 14 industry sources into deterministic decision gates, schemas, and worked test examples.
ainb-fleet:daemons
Runtime-health view of the four fleet daemons — phone bridge, notifyd, ATC, and the fleet auto-continue daemon — in one table. Each row reports state (running / stopped / unknown), pid, uptime, last activity, error count, and a HEALTH reason that distinguishes a clean stop from a crash (stale heartbeat) or a…
test-coverage
Use after writing tests to assess coverage quality across structural, mutation, requirements, and API/integration dimensions; organized knowledge for choosing and interpreting coverage analyses.
apply-anthropic-skill-best-practices
Comprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structure.