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 sd0xdev/sd0x-harness --skill next-stepgit clone --depth 1 https://github.com/sd0xdev/sd0x-harnessWrote 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/sd0xdev/sd0x-harness/next-step)<a href="https://agentmods.dev/skills/sd0xdev/sd0x-harness/next-step"><img src="https://agentmods.dev/badge/skills/sd0xdev/sd0x-harness/next-step/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/sd0xdev/sd0x-harness/next-step"><img src="https://agentmods.dev/badge/skills/sd0xdev/sd0x-harness/next-step.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 61 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00063 | $0.01559 |
| Opus 5.5 | $0.00025 | $0.00624 |
| Sonnet 5.5 | $0.00013 | $0.00312 |
| Haiku 4.5 | $0.00006 | $0.00156 |
Grade A, and why
next-step 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 1mo 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Next Step Advisor
When NOT to Use
- Auto-loop already handling review/precommit flow (hooks track and assist)
- User gave a clear, specific instruction (just do it)
- Mid-execution of a skill workflow (follow that skill's progression)
Procedure
- Run
bash scripts/run-skill.sh next-step analyze.jsto collect deterministic findings - Parse the JSON output — findings, gates, diff summary, phase, feature_context, next_actions, backlog
- If P0/P1 findings exist → format top 3 as actionable suggestions (Findings Mode)
- If mid-pipeline (gates not all passed, no P0/P1) → use progression tables to suggest next step
- If phase = post_precommit → suggest doc sync + request update (use next_actions)
- If phase = feature_complete → output feature complete summary with backlog
- If all gates pass and no P0/P1 → output session summary with commit seed (Summary Mode, P2/P3 shown as oversights)
Script Integration
The analyze script runs 18 deterministic heuristics against git state, review state, and feature context:
| Priority | Heuristics | Meaning |
|---|---|---|
| P0 | Gate missing (code review, doc review, precommit) | Required steps not completed |
| P1 | Test gap, security hotspot, migration risk, doc-sync-needed, request-stale, corpus-unreadable | Important oversights |
| P2 | README missing, skill-lint needed, locale drift, mixed concerns, ac-incomplete, intent-advisory (planning docs without exact intent-.md) | Quality improvements |
| P3 | Main branch warning, requirements-advisory, feature-complete | Informational |
The script exits with code 0 (no P0/P1), 1 (has P1), or 2 (has P0).
Output Fields (v2)
| Field | Type | Description |
|---|---|---|
| phase | string | mid_development / post_precommit / ready_to_commit / feature_complete / clean |
| feature_context | object | { key, source, confidence, docs_path, has_tech_spec, has_requirements, has_requests } |
| next_actions | array | [{ id, command, args, reason, confidence }] sorted by confidence desc |
| backlog | object/null | { total_features, incomplete_features } — only when phase = feature_complete |
What ships with it
2 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.
- 1mo ago First seen · 156 lines · 63 tokens per session scan A b8fc41d2b49c
next-step is a skill published in the GitHub repository sd0xdev/sd0x-harness (194 stars, last pushed 12d ago), licensed MIT. It adds 63 tokens to every session and 1,559 once invoked, about $0.0003 per session on Opus 5.5. 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
comet-safe-delivery
A Chinese-language procedure for safely delivering specified Comet changes through Git. It covers checking worktrees and unrelated edits, staging exact files, validating hooks, and authorized commits or pushes.
update
Safe cc10x upgrade through the Claude Code plugin CLI. Lists every installed scope, refreshes the marketplace, updates each scope, and optionally carries local patches over to the new install. Use this skill when: updating cc10x, upgrading, pulling latest cc10x, syncing plugin, refreshing cache, or checking for new…
resolving-merge-conflicts
Use when a git merge or rebase reports conflicts and the operation is in progress.
vibe-cherry-pick-integration
Safely integrates commits from parallel agent branches using sequential cherry-pick. Use after parallel work completes in isolated branches or worktrees.
vibe-pre-commit-audit
Scans staged changes for secrets, debug statements, TODOs without references, and other common commit mistakes. Use before creating any commit.
codely-plan-phase-implement-github
Implement one phase of a plan stored as GitHub issues in the repository of the current working directory. Given the URL of a phase (child) issue it implements that phase; given the parent plan issue it finds and implements the current phase. Only implements a single phase per invocation, then stops for user review. It…