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 MichaelYcJo/SpecSeal --skill feature-plannergit clone --depth 1 https://github.com/MichaelYcJo/SpecSealWrote 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/michaelycjo/specseal/feature-planner)<a href="https://agentmods.dev/skills/michaelycjo/specseal/feature-planner"><img src="https://agentmods.dev/badge/skills/michaelycjo/specseal/feature-planner/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/michaelycjo/specseal/feature-planner"><img src="https://agentmods.dev/badge/skills/michaelycjo/specseal/feature-planner.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 | $0.00088 | $0.00584 |
| Opus 5.5 | $0.00035 | $0.00234 |
| Sonnet 5.5 | $0.00018 | $0.00117 |
| Haiku 4.5 | $0.00009 | $0.00058 |
Grade A, and why
feature-planner 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 7d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
feature-planner, write the scope down before it moves
Scope that lives in someone's head grows quietly, and nobody can point to when it did. Decomposing the work orders it; writing down what is not in it is what makes the boundary hold later.
Planning Steps
1. Requirements Clarification
- What exactly is being requested?
- What's explicitly NOT in scope?
- What are the acceptance criteria?
- Any constraints (performance, compatibility, timeline)?
2. Existing Code Analysis
- What related code already exists?
- What patterns does the project use?
- What can be reused or extended, and what is built new?
- What will break if X changes?
3. Implementation Plan
- Break into ordered tasks (dependencies mapped)
- Identify parallel and sequential work
- Estimate which files change
- Flag risky parts that need extra care
4. Scope Lock
- List what's IN scope (explicit)
- List what's OUT of scope (explicit)
- Get user confirmation before starting
Rules
- No gold-plating: plan only what's requested
- Identify the MVP path first
- Flag unknowns early (don't discover them mid-implementation)
- Where more than ten files are affected, suggest a phased approach
Where the output goes
Into seal/specs/<work-item-id>/plan.md, as its Phases table: one row per phase,
with the Verified by and Status columns that table carries. There is
no separate task-list file and no separate root for one.
What that costs: a phase row holds an ordered slice, not a dependency graph, so the parallel markers in the format below do not survive into the file. They are for the conversation that produces the plan. Work finishing in one session needs no file at all.
Output Format
## Feature: [name]
**Scope**: [in]
**Not**: [out]
**Tasks** (in order):
1. [task], files: [files affected]
2. [task], files: [files affected]
(depends on task 1)
3. [task], files: [files affected] (parallel with task 2)
**Risks**: [what could go wrong]
**Questions**: [what needs user input]
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.
- 7d ago Changed · +1 lines · +5 tokens per session d7c4eaa2b235
- 1mo ago Changed · +2 tokens per session 26b36ddb43d0
- 1mo ago Changed · +4 lines da9308be357f
- 2mo ago First seen · 73 lines · 81 tokens per session scan A 9eae02cf9b8a
feature-planner is a skill published in the GitHub repository MichaelYcJo/SpecSeal (1 stars, last pushed 4d ago), licensed MIT. It adds 88 tokens to every session and 584 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
critical-code-reviewer
Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
pr-review
Comprehensive PR review across six dimensions — cost impact, environment drift, ownership gaps, SOC 2 compliance, deprecated API / version hygiene, and rollback feasibility. Each mode inspects the diff and current file state, reports findings with severity, and recommends concrete fixes. Use when preparing a PR for…
pr-review
Use when the user wants to deeply review a pull/merge request or a local diff — "review this PR", "grill the MR", "stress-test this diff", "deep-dive code review", "code review before merge", or when they name a PR/MR URL, number, branch, commit range (A..B/A...B), tag or SHA. Works on GitHub (gh), GitLab (glab), or a…
genshijin-review
A compact pull-request review format that writes one actionable finding per line in Japanese or English.
skill-distiller
Fetches top-rated skills from skills.sh, analyzes them, and synthesizes one token-efficient skill combining the best elements. Use when the user asks to "distill skills for X", "find and combine skills for X", "synthesize skills", "merge skills", "make a skill for X from skills.sh", "update distilled skill", or…