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/michaelycjo/specseal/implementnpx skills add MichaelYcJo/SpecSeal --skill implementgit clone --depth 1 https://github.com/MichaelYcJo/SpecSealWhat 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 | $0.00131 | $0.06678 |
| Opus 5 | $0.00066 | $0.03339 |
| Sonnet 5 | $0.00026 | $0.01336 |
| Haiku 4.5 | $0.00013 | $0.00668 |
Grade A, and why
implement 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 2d 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 — 527 lines — stays where its author put it; the contents beside it link to each section on GitHub.
implement — spec-driven implementation
Methodology for implementing against written specs, leaving durable evidence,
and closing the loop with review. Loaded by the smith agent; usable directly.
Document layout — three axes
Every artifact this skill produces goes to exactly one of three roots, split by lifetime, not by who wrote it:
| Root | Lifetime | Test | Authority |
|---|---|---|---|
docs/ |
Permanent, cumulative | Must still be true in 6 months | Norms, ratified by humans. Read when the repository has them; never created here — a project's documentation convention is its own |
specs/ |
One work item | Its role ends when this work ships (SDD, overview) | The contract this work executes against. A human approves plan.md, which is why this is a repository document and not tool state |
.specseal/ |
Mixed — see below | Everything this plugin maintains | Written and read by machines: the map, the migration config, the follow-up list, task lists |
The axis is lifetime and authority, not audience — humans and AI read all three. (Labeling policies "for humans" would push sessions away from reading them, and policy outranks everything else when a repository has it.)
.specseal/ is committed — gitignored files do not follow worktrees or other
machines — and its existence is what tells the gates this repository runs the
workflow. Inside it, lifetimes differ:
.specseal/
├── map.md permanent — spec clause ↔ code coordinates (split into map/ if it grows)
├── parity.md permanent — migration config, only when declared
├── follow-up.md permanent — schedulable items in a repository with no tracker
└── tasks/ one change
The review round records are not here. They live beside the work item they
are about, in specs/<work-item-id>/, together with the routing declaration
and the rest of the SDD set:
specs/<work-item-id>/
├── routing.md the routing answer, written before the first edit
├── spec.md · plan.md · questions.md · overview.md
├── round-N.md one review round — closed at merge and kept
└── tests-todo.md · evidence-todo.md
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.
- 2d ago First seen · 527 lines · 131 tokens per session scan A 509b27ff5408
implement is a skill published in the GitHub repository MichaelYcJo/SpecSeal (1 stars, last pushed 2d ago), licensed MIT. It adds 131 tokens to every session and 6,678 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
gsd-audit-milestone
Audit milestone completion against original intent before archiving.
spec-kitty-charter-doctrine
Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…
conductor-implement
Executes the tasks defined in the specified track's plan. Use this to start or continue working on a feature, bug fix, or chore.
api-design
Design or review an HTTP/REST/GraphQL API for versioning, pagination, error shapes, idempotency, auth, status codes, cache headers, and breaking-change management. Use when asked to "design an API", "shape the endpoints", "design the schema", "add a new endpoint", "review this API", or when building/modifying a public…
create-mcp-server
Build, iterate, and evaluate Model Context Protocol (MCP) servers that expose external services as tools an LLM can call. Covers schema/tool design, error handling, pagination, MCP Inspector testing, and an eval set. Use when asked to "build an MCP server", "create an MCP tool", "wrap this API as MCP", "expose X to…
dependency-upgrade
Plan, batch, and verify dependency upgrades safely. Triages outdated packages into risk tiers, upgrades in order (dev/minor/patch first, runtime majors last), verifies each batch, and produces an auditable commit sequence. Use when asked to "upgrade deps", "bump packages", "update nodemodules", "fix vulnerabilities"…