Is sequential-think safe to install?

SaferSkills independently audited sequential-think (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

CategoryWeightCategory scoreContribution

Securityprompt, exec, net, exfil, eval

35%

100

35.0 pts

Supply chainhash, typosquat, maintainer, lockfile

20%

100

20.0 pts

Maintenancestaleness, pinning, CI

15%

100

15.0 pts

TransparencySKILL.md, perms, README

15%

100

15.0 pts

Communityinstalls, verify, response

15%

100

15.0 pts

Findings & checks · 0 flagged

Securityscore 100 · 0 findings

✓—All security checks passedNo findings in this category for the latest scan.pass

Supply chainscore 100 · 0 findings

✓—All supply chain checks passedNo findings in this category for the latest scan.pass

Maintenancescore 100 · 0 findings

✓—All maintenance checks passedNo findings in this category for the latest scan.pass

Transparencyscore 100 · 0 findings

✓—All transparency checks passedNo findings in this category for the latest scan.pass

Communityscore 100 · 0 findings

✓—All community checks passedNo findings in this category for the latest scan.pass

The primary manifest — the file an agent reads to learn what this artifact does.

skills/sequential-think/SKILL.md · 1 file

skills/sequential-think/SKILL.md5.8 KB · Markdown

name: sequential-think

description: |

Multi-step reasoning engine for complex analysis and systematic problem solving. Use when: (1) Complex debugging scenarios with multiple layers, (2) Architectural analysis and system design, (3) Problems requiring hypothesis testing and validation, (4) Multi-component failure investigation, (5) Performance bottleneck identification. Triggers: "--think", "--think-hard", "--ultrathink", "analyze step by step", "break down this problem", "systematic analysis". IMPORTANT: Do NOT use for simple single-step tasks.

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: false when truly finished
Must have satisfactory, verified answer
Don't rush to conclusion

When to Use

Scenario	Use Sequential Think
Complex debugging (3+ layers)	✅ Yes
Architectural analysis	✅ Yes
Multi-component investigation	✅ Yes
Performance bottleneck analysis	✅ Yes
Root cause analysis	✅ Yes
Simple explanation	❌ No
Single-file change	❌ No
Straightforward fix	❌ No

Parameters

Parameter	Type	Required	Description
`thought`	string	Yes	Current thinking step content
`thoughtNumber`	int	Yes	Current position in sequence (1-based)
`totalThoughts`	int	Yes	Estimated total thoughts needed
`nextThoughtNeeded`	bool	No	Whether more thinking needed (default: true)
`isRevision`	bool	No	Whether this revises previous thinking
`revisesThought`	int	No	Which thought number is being reconsidered
`branchFromThought`	int	No	Branching point thought number
`branchId`	string	No	Identifier for current branch
`needsMoreThoughts`	bool	No	Signal that more thoughts needed beyond estimate

Output Format

{
  "thoughtNumber": 3,
  "totalThoughts": 5,
  "nextThoughtNeeded": true,
  "branches": ["alt-approach"],
  "thoughtHistoryLength": 3
}

Workflow Pattern

Phase 1: Problem Decomposition

Thought 1: Identify problem scope and constraints
Thought 2: Break into sub-problems
Thought 3: Identify dependencies between sub-problems

Phase 2: Hypothesis Generation

Thought 4: Generate initial hypothesis
Thought 5: Identify evidence needed to verify

Phase 3: Verification & Iteration

Thought 6: Test hypothesis against evidence
Thought 7: Revise if needed (isRevision=true)
Thought 8: Branch if alternative path promising

Phase 4: Conclusion

Final Thought: Synthesize findings, provide answer (nextThoughtNeeded=false)

Best Practices

Start with estimate, adjust as needed

Initial totalThoughts is just a guess
Increase if problem more complex than expected
Decrease if solution found early

Use revisions for course correction

Mark isRevision=true when reconsidering
Reference revisesThought for clarity

Branch for alternative approaches

Use branchFromThought to explore alternatives
Give meaningful branchId names

Filter irrelevant information

Each thought should advance toward solution
Ignore tangential details

Don't rush completion

Only nextThoughtNeeded=false when truly done
Verify hypothesis before concluding

Anti-Patterns

Prohibited	Correct
Use for simple tasks	Reserve for complex multi-step problems
Skip thought numbers	Always increment correctly
Conclude without verification	Verify hypothesis before final thought
Ignore previous thoughts	Build upon or explicitly revise
Fixed totalThoughts	Adjust as understanding evolves

Integration with Other Tools

With ACE-Tool

ACE-Tool → align current state → Sequential Think → analyze and plan

With Context7

Sequential Think → coordinate analysis → Context7 → provide official patterns

With Serena

Serena → symbol-level exploration → Sequential Think → systematic analysis

sequential-think— agent skill

Is sequential-think safe to install?

Sequential Think

Execution Methods

Core Principles

Iterative Thinking Process

Dynamic Thought Count

Hypothesis-Driven Approach

Completion Criteria

When to Use

Parameters

Output Format

Workflow Pattern

Phase 1: Problem Decomposition

Phase 2: Hypothesis Generation

Phase 3: Verification & Iteration

Phase 4: Conclusion

Best Practices

Anti-Patterns

Integration with Other Tools

With ACE-Tool

With Context7

With Serena

Audit the pieces. Scan the whole. Decide.