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 skills/dianel555/dskills/sequential-thinknpx skills add Dianel555/DSkills --skill sequential-thinkgit clone --depth 1 https://github.com/Dianel555/DSkillsWrote 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/dianel555/dskills/sequential-think)<a href="https://agentmods.dev/skills/dianel555/dskills/sequential-think"><img src="https://agentmods.dev/badge/skills/dianel555/dskills/sequential-think.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 | $0.00110 | $0.01385 |
| Opus 5 | $0.00055 | $0.00692 |
| Sonnet 5 | $0.00022 | $0.00277 |
| Haiku 4.5 | $0.00011 | $0.00138 |
Grade A, and why
sequential-think 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 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.
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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sequential Think
Structured iterative thinking for complex problem-solving. Standalone CLI only (no MCP dependency).
Execution Methods
Run scripts/sequential_think_cli.py via Bash:
# Process a thought
python scripts/sequential_think_cli.py think \
--thought "First, let me analyze the problem structure..." \
--thought-number 1 \
--total-thoughts 5
# Continue thinking chain
python scripts/sequential_think_cli.py think \
--thought "Based on step 1, I hypothesize that..." \
--thought-number 2 \
--total-thoughts 5
# Revise a previous thought
python scripts/sequential_think_cli.py think \
--thought "Reconsidering step 1, I realize..." \
--thought-number 3 \
--total-thoughts 5 \
--is-revision \
--revises-thought 1
# Branch into alternative path
python scripts/sequential_think_cli.py think \
--thought "Alternative approach: what if we..." \
--thought-number 4 \
--total-thoughts 6 \
--branch-from 2 \
--branch-id "alt-approach"
# Final thought (complete chain)
python scripts/sequential_think_cli.py think \
--thought "Conclusion: the solution is..." \
--thought-number 5 \
--total-thoughts 5 \
--no-next
# View thought history
python scripts/sequential_think_cli.py history [--format json|text]
# Clear thought history
python scripts/sequential_think_cli.py clear
Core Principles
Iterative Thinking Process
- Each tool call = one "thought" in the chain
- Build upon, question, or revise previous thoughts
- Express uncertainty when it exists
Dynamic Thought Count
- Start with initial estimate of
totalThoughts - Adjust up/down as understanding evolves
- Add more thoughts even after reaching initial end
Hypothesis-Driven Approach
- Generate hypotheses as potential solutions emerge
- Verify hypotheses based on chain-of-thought steps
- Repeat until satisfied with solution
Completion Criteria
- Only set
nextThoughtNeeded: falsewhen truly finished - Must have satisfactory, verified answer
- Don't rush to conclusion
What ships with it
3 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.
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 · 195 lines · 110 tokens per session scan A c23214e8150c
sequential-think is a skill published in the GitHub repository Dianel555/DSkills (64 stars, last pushed yesterday), licensed MIT. It adds 110 tokens to every session and 1,385 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
code-intelligence
Use when navigating or refactoring code with a language server - choosing between semantic (LSP), exact-text (rg), and fuzzy/semantic search; anchoring LSP calls by position; gating degraded results; and disclosing tool substitutions, in any language.
casely
Intelligent QA assistant that automates writing test cases from project documentation. Use when the user wants to generate test cases from requirements, runs /init, /parse, /style, /plan, /generate, /export, or works with PDF/DOCX/XLSX requirement documents and TestRail-ready Excel export.
battle-tested-engineer
Engineering judgment for code write/refactor/test and frontend UI. Trigger on code review, legacy cleanup, tests, UI with data, bloat/over-engineer complaints — even with no explicit mention, before any diff/rewrite/test suite. Output ultra-terse caveman style; code, commits, PR desc, security warnings stay normal…
geekx-gate
当用户审查需求、工程计划、架构提案、路线图、最小可行范围或智能体输出，并担心过度设计、范围过大、未来假设太多、缺少非目标、缺少必要性证据，或想判断重写、框架、插件系统、工作流引擎、多智能体架构、模块边界等难撤回技术决定现在该不该做时使用。典型触发词：必要性审判、反过度设计、范围审查、砍噪音、最小必要升级、复杂度税、承诺闸门、技术决定、重写、开庭、多线程审判。.
geekx-grilling
当用户希望通过连续追问压力测试计划、决定、想法、需求或方案，要求 grill me、grilling、拷问我、追问到底、挑战假设、梳理决策树，或需要在行动前逐项消除关键歧义时使用。尤其适合存在多个选项、依赖关系、过度设计风险或尚未形成共同理解的场景。.
lazarus-mode
Use when the user asks for expert-level engineering judgment, "X mode", seasoned/staff/principal engineer standards, robust architecture, security/performance/reliability/scalability scrutiny, optimization review, rigorous implementation and release discipline, or when combining implementation work with…