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 ngocsangyem/MeowKit --skill sequential-thinkinggit 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/skills/ngocsangyem/meowkit/sequential-thinking)<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/sequential-thinking"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/sequential-thinking/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/ngocsangyem/meowkit/sequential-thinking"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/sequential-thinking.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 | $0.00079 | $0.01076 |
| Opus 5 | $0.00039 | $0.00538 |
| Sonnet 5 | $0.00016 | $0.00215 |
| Haiku 4.5 | $0.00008 | $0.00108 |
Grade A, and why
mk:sequential-thinking 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sequential Thinking
Structured step-by-step reasoning with hypothesis generation, elimination, and revision capability.
When to Use
- Complex problem requiring multi-step reasoning
- Debugging where root cause isn't obvious
- When mk:fix invokes diagnosis (Phase 3)
- Architecture decisions with multiple trade-offs
- Any situation where "I think it's X" needs evidence before acting
Do NOT use for: trivial fixes (typo, lint), single-file changes with obvious cause.
Process
- State the problem — what is observed vs expected
- Generate hypotheses — from evidence, NOT guessing. Each hypothesis needs: what evidence would confirm it, what would refute it
- Test hypotheses — use Grep/Read/Bash to find evidence for/against each
- Eliminate — mark each CONFIRMED, REFUTED, or INCONCLUSIVE with evidence
- Conclude — state root cause with confidence level + evidence chain
- Scope the fix — what must change to address root cause (not symptoms)
Adjust dynamically: expand if more complex than expected, contract if simpler.
Output Format
Use references/hypothesis-testing.md template. Key sections:
## Sequential Analysis: [problem]
### Hypotheses
| # | Hypothesis | Evidence for | Evidence against | Status |
| --- | ---------- | ------------ | ---------------- | ------ |
### Root Cause
Confirmed: [root cause]
Confidence: [high/medium/low]
Evidence: [what confirms this]
### Fix Scope
[what must change — files, functions, logic]
Revision & Branching
When new evidence invalidates a previous conclusion:
- Mark revision explicitly:
[REVISION of Hypothesis N]: [correction + why] - When 2+ approaches viable: branch, evaluate each, converge with decision
Load references/core-patterns.md for revision/branching patterns.
For advanced techniques (spiral refinement, multi-branch convergence): references/advanced-techniques.md
For uncertainty + revision cascades: references/advanced-strategies.md
For concrete examples: references/examples-debug.md, examples-api.md, examples-architecture.md
What ships with it
14 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.
- references/advanced-strategies.md 1.5 KB
- references/advanced-techniques.md 2.3 KB
- references/core-patterns.md 1.6 KB
- references/examples-api.md 2.2 KB
- references/examples-architecture.md 2.6 KB
- references/examples-debug.md 2.4 KB
- references/five-whys-plus.md 4.7 KB
- references/gotchas.md 921 B
- references/hypothesis-testing.md 2.5 KB
- references/kepner-tregoe.md 7.4 KB
- references/scientific-method.md 3.7 KB
- scripts/format-thought.js 4.8 KB runs code
- scripts/process-thought.js 6.4 KB runs code
- scripts/test-scripts.sh 3.2 KB runs code
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 · 125 lines · 79 tokens per session scan A 598ddb1664e4
mk:sequential-thinking is a skill published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 1,076 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 2026-09-03.
Other skills, from other repositories
audit
Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.
investigate
Investigate bugs and errors in Elixir/Phoenix — root-cause analysis for crashes, exceptions, stack traces, test failures. Use --parallel for deep 4-track investigation.
narrow-bare-rescue
Narrow bare rescue in Elixir so real errors like KeyError and typos propagate instead of being swallowed. Use to audit rescues and refactor error handling.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
verify
Verify Elixir/Phoenix changes — compile, format, and test in one loop. Use after implementation, before PRs, or after fixing bugs.
phx-investigate
Investigate Elixir/Phoenix bugs root-cause first. Reproduce failures, cite evidence, and use optional Amp subagents only when useful.