Install
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/ngocsangyem/meowkit/agents_indexgit clone --depth 1 https://github.com/ngocsangyem/MeowKitWrote 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/agents/ngocsangyem/meowkit/agents_index)<a href="https://agentmods.dev/agents/ngocsangyem/meowkit/agents_index"><img src="https://agentmods.dev/badge/agents/ngocsangyem/meowkit/agents_index.svg" alt="Measured on agentmods" height="20"></a> Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,826 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost
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 | $0.00000 | $0.02826 |
| Opus 5 | $0.00000 | $0.01413 |
| Sonnet 5 | $0.00000 | $0.00565 |
| Haiku 4.5 | $0.00000 | $0.00283 |
Security
Grade A, and why
AGENTS_INDEX scanned grade A 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`evaluator.md`|Core|Behavioral active-verification of running builds against rubric library; skeptic persona; produces graded verdict with concrete runtime evidence (screenshots/curl/CLI). Distinct from reviewer (structu .claude/agents/AGENTS_INDEX.md · 85 lines
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
the toolkit Agents Index
Active Agents
Agent registry views (generated): 18 core/support direct-only; 21 domain hub-only; 1 intelligence direct-only; 1 intelligence direct-and-harness; 1 internal harness.
[42]{agent_file,type,role,source,workflow_phases,auto_activate,ce_version,last_improved}
`orchestrator.md`|Core|Task router, complexity classification, model tier assignment|original|Phase 0 (Orient)|Yes — every task|260326|260326
`explore.md`|Support|Fast read-only codebase search and orientation: locates code, traces call/data paths, reports `path:line` evidence|original|Phase 0 (Orient), any|Routed by orchestrator or explicit|260725|260725
`planner.md`|Core|Two-lens planning (product + engineering) + product-level mode for green-field builds, Gate 1 enforcement|original|Phase 1 (Plan)|Routed by orchestrator|260326|260408
`brainstormer.md`|Support|Solution brainstorming, architecture evaluation, trade-off analysis|Credit: Duy Nguyen|Phase 1 (Plan)|Routed by orchestrator or explicit|260326|260326
`advisor.md`|Support|Reframe-then-recommend advisory executor: interviews one question per turn, confirms the real problem, emits ONE verdict packet|original|on-demand|Invoked ONLY by mk:advise — never orchestrator-routed|260715|260715
`athena.md`|Intelligence|Strategic intelligence and lifecycle supervisor: assesses difficult situations, recommends an operational direction, then GUIDE/RESCUE/REVIEW/RECHECK for an opted-in run; holds no gate authority|original|on-demand|Explicit direct consult where runtime supports it, or named `--advice` checkpoints; never orchestrator-routed|260726|260726
`researcher.md`|Support|Technology research, library evaluation, documentation gathering|Credit: Duy Nguyen|Phase 0, 1, 4|Routed by orchestrator or explicit|260326|260326
`architect.md`|Core|ADR generation, system design, architecture review|original|Phase 1 (Plan)|Routed by orchestrator for complex tasks|260326|260326
`tester.md`|Core|Test writing; TDD enforcement (red/green/refactor) when `--tdd` / `MEOWKIT_TDD=1`; non-blocking test writing in default mode|original|Phase 2 (Test)|Routed by orchestrator (always in TDD mode; on-request in default mode)|260326|260409
`security.md`|Core|Risk-triggered deep security audit, BLOCK verdicts, platform-specific rules; deterministic post-write scan|original|Phase 2, 4|Deep audit on flagged risk surfaces; post-write scan on every write|260326|260326
`developer.md`|Core|Implementation per approved plan; strict TDD when `--tdd` / `MEOWKIT_TDD=1`; direct implementation in default mode; self-healing|original|Phase 3 (Build)|Routed by orchestrator (after tester in TDD mode; directly after planner in default mode)|260326|260409
`ui-ux-designer.md`|Support|UI design, design systems, accessibility, responsive layouts|original|Phase 3 (Build GREEN)|Routed when frontend detected|260326|260330
`reviewer.md`|Core|5-dimension code review, Gate 2 enforcement, adversarial personas, artifact verification|original|Phase 4 (Review)|Routed by orchestrator after developer|260326|260331
`evaluator.md`|Core|Behavioral active-verification of running builds against rubric library; skeptic persona; produces graded verdict with concrete runtime evidence (screenshots/curl/CLI). Distinct from reviewer (structural).|original|Phase 3 (active verification) + Phase 4 (contract reviewer)|Routed by harness after generator iteration; explicit via /mk:evaluate|260408|260408
`shipper.md`|Core|Deployment pipeline, conventional commits, PR creation|original|Phase 5 (Ship)|Routed by orchestrator after Gate 2|260326|260326
`git-manager.md`|Support|Git operations: stage, commit, push with conventional commits|Adapted from external skill patterns|Phase 5 (Ship), any|On "commit"/"push" request|260329|260329
`documenter.md`|Core|Living documentation, changelog generation, docs sync|original|Phase 6 (Reflect)|Routed by orchestrator after ship|260326|260326
`analyst.md`|Core|Cost tracking, pattern extraction, lessons learned|original|Phase 0, 6|Auto at session start/end|260326|260326
`journal-writer.md`|Support|Failure documentation, root cause analysis, lessons|Credit: Duy Nguyen|Phase 6 (Reflect), escalations|On failure/escalation|260326|260326
`project-manager.md`|Core|Cross-workflow delivery tracking, evidence-based status reports|original|on-demand (0–6)|Explicit delegation, `/mk:status`, or `post-phase-delegation.md` rule|260422|260422
`jira-issue.md`|Domain|JIRA issue CRUD via jira-as wrapper (create/get/update/delete)|Adapted from JIRA-Assistant-Skills v4.0.1|on-demand|Forked from `mk:jira-issue` skill|260510|260510
`jira-search.md`|Domain|JIRA search + filter management via jira-as (JQL query/validate/build/export, saved filters)|Adapted from JIRA-Assistant-Skills v4.0.1|on-demand|Forked from `mk:jira-search` skill|260510|260510
`jira-lifecycle.md`|Domain|Workflow lifecycle: transition / assign / resolve / reopen / version / component|Adapted from JIRA-Assistant-Skills v4.0.1|on-demand|Forked from `mk:jira-lifecycle` skill|260510|260510
`jira-collaborate.md`|Domain|Comments, attachments, watchers, notifications|Adapted from JIRA-Assistant-Skills v4.0.1|on-demand|Forked from `mk:jira-collaborate` skill|260510|260510
`jira-relationships.md`|Domain|Issue links, blockers, dependencies, clone, bulk-link|Adapted from JIRA-Assistant-Skills v4.0.1|on-demand|Forked from `mk:jira-relationships` skill|260510|260510
`jira-time.md`|Domain|Time tracking: log / worklogs / estimates / reports / bulk-log|Adapted from JIRA-Assistant-Skills v4.0.1|on-demand|Forked from `mk:jira-time` skill|260510|260510
`jira-agile.md`|Domain|Agile: epics / sprints / backlog / rank / story-points / subtasks / velocity|Adapted from JIRA-Assistant-Skills v4.0.1|on-demand|Forked from `mk:jira-agile` skill|260510|260510
`jira-fields.md`|Domain|Custom field discovery + agile field configuration|Adapted from JIRA-Assistant-Skills v4.0.1|on-demand|Forked from `mk:jira-fields` skill|260510|260510
`jira-bulk.md`|Domain|Bulk JIRA ops (10+ issues) — dry-run mandatory first|Adapted from JIRA-Assistant-Skills v4.0.1|on-demand|Forked from `mk:jira-bulk` skill|260510|260510
`jira-jsm.md`|Domain|Service Management: queues, SLAs, customers, requests, approvals (8 sub-domains)|Adapted from JIRA-Assistant-Skills v4.0.1|on-demand|Forked from `mk:jira-jsm` skill|260510|260510
`jira-admin.md`|Domain|Project / user / group / scheme / automation administration (11 sub-domains)|Adapted from JIRA-Assistant-Skills v4.0.1|on-demand|Forked from `mk:jira-admin` skill|260510|260510
`jira-dev.md`|Domain|Dev artifacts: branch-name, PR-description, parse-commits, link-commit/PR|Adapted from JIRA-Assistant-Skills v4.0.1|on-demand|Forked from `mk:jira-dev` skill|260510|260510
`jira-ops.md`|Domain|Diagnostic: cache-status / cache-clear / discover-project|Adapted from JIRA-Assistant-Skills v4.0.1|on-demand|Forked from `mk:jira-ops` skill|260510|260510
`jira-evaluator.md`|Intelligence|Ticket complexity + inconsistency analysis (read-only)|Adapted from the toolkit jira/agents/ (skill-scoped → project-scoped, MCP→jira-as)|on-demand|Forked from `mk:jira-evaluator` skill|260510|260510
`jira-estimator.md`|Intelligence|Heuristic story-point estimation (read-only)|Adapted from the toolkit jira/agents/|on-demand|Forked from `mk:jira-estimator` skill|260510|260510
`jira-analyst.md`|Intelligence|Full ticket context analysis incl. media (read-only)|Adapted from the toolkit jira/agents/|on-demand|Forked from `mk:jira-analyst` skill|260510|260510
`story-sizer.md`|Intelligence|Pre-ticket Fibonacci sizing of paste-mode user stories. Read-only at Jira; auto-create delegates to `mk:jira-issue` + `mk:jira-collaborate`.|New in v2.9.0|on-demand|Forked from `mk:story-sizer` skill|260511|260511
`confluence-bulk.md`|Support|Execute bulk Confluence operations (bulk-label, bulk-move, bulk-delete) via confluence-as CLI; dry-run mandatory first|Adapted from Confluence-Assistant-Skills|on-demand|Routed by mk:confluence hub|260530|260530
`confluence-collaborate.md`|Support|Manage Confluence collaboration surface: comments, attachments, labels, watchers|Adapted from Confluence-Assistant-Skills|on-demand|Routed by mk:confluence hub|260530|260530
`confluence-page.md`|Support|Confluence page CRUD, hierarchy, and version ops via confluence-as CLI wrapper|Adapted from Confluence-Assistant-Skills|on-demand|Routed by mk:confluence hub|260530|260530
`confluence-search.md`|Support|Find Confluence pages by criteria via confluence-as CLI; CQL filter management and space operations|Adapted from Confluence-Assistant-Skills|on-demand|Routed by mk:confluence hub|260530|260530
`confluence-spec-analyst.md`|Intelligence|Read full Confluence spec page and produce structured Spec Research Report with requirements, ACs, gaps, and user stories (read-only)|Adapted from Confluence-Assistant-Skills|on-demand|Routed by mk:confluence hub|260530|260530
Changes
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.
- 5d ago First seen · 85 lines · 0 tokens per session scan A f5088fca09f0
AGENTS_INDEX is an agent published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,826 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Related
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.