Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add MichaelYcJo/SpecSeal/plugin install 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/config)<a href="https://agentmods.dev/skills/michaelycjo/specseal/config"><img src="https://agentmods.dev/badge/skills/michaelycjo/specseal/config/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/config"><img src="https://agentmods.dev/badge/skills/michaelycjo/specseal/config.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 | $0.00051 | $0.02651 |
| Opus 5.5 | $0.00020 | $0.01060 |
| Sonnet 5.5 | $0.00010 | $0.00530 |
| Haiku 4.5 | $0.00005 | $0.00265 |
Grade A, and why
config 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 4d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/specseal:config, what this repository decided and how to decide otherwise
seal/config.md holds what a repository says about itself. Every row has a
default, and an absent row is not an error. A person runs this command to see
every row and to change one; the session running it follows the procedure
below. First setup asks its questions once and never again, and this command
is how a person answers them again later.
Where the file is
<repo>/seal/config.md where that directory exists, and
$(git rev-parse --git-common-dir)/seal/config.md otherwise: local mode,
where the root sits under the common git directory. Resolve it that way rather
than spelling the first place and stopping.
No root at either place means this repository has not been set up. Say so,
name the implement skill's bootstrap as what does it, and stop. Do not
create the file: its presence at one of those two places is what opts a
repository in, and creating it here would opt somebody in from a command they
ran to look.
Procedure
1. Show every row, present or not. Read the file, and print every row of the table below with its current value, including the ones the file does not carry, with the default and where it comes from. A row a repository never set is the most likely one somebody wants to change, and showing only what is present hides exactly those.
| Row | Default | What it governs |
|---|---|---|
Commit and pull request language |
English | the commit subject and body, the pull request title and body, and a review report posted as a pull-request comment |
Record language |
English | the prose in spec.md, plan.md, overview.md, questions.md, changelog.md, and a round record's cells |
Mode |
the folder decides | which of the two places the root should live at |
Broad gate |
none: broad-gate refuses without it |
the one shell command line broad-gate runs once the review rounds settle: the full suite, the repository-wide lint, the typecheck |
Document token ceiling |
not declared: no length is checked | the estimated tokens past which fold-check reports a top-level policy document as one to split |
Policy root |
docs |
the directory of the ratified policy documents, which the settle writes |
Reference specs |
every directory named specs outside the root |
the directories this repository kept its own specifications in, which the plugin reads as history and never takes |
Pact |
none: no pact is held elsewhere | the origin remote URL of the repository holding a pact this repository signs, several separated by ; |
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.
- 4d ago Changed · +3 lines fc4d5f0f0e9b
- 7d ago Changed · -3 lines · +2 tokens per session 6bd53a39b1dd
- 12d ago Changed 93b66d4140ef
- 14d ago Changed · -1 lines a4ca00d29900
- 17d ago Changed · +14 lines 8a40a4d27f42
- 24d ago Changed 7bd09f7d71dd
- 27d ago Changed · +8 lines b876252f9e52
- 1mo ago Changed · +9 lines dcb853dc6b28
- 1mo ago Changed · +14 lines 2627c3cd4e67
- 1mo ago First seen · 136 lines · 49 tokens per session scan A 6961b01db9aa
config is a skill published in the GitHub repository MichaelYcJo/SpecSeal (1 stars, last pushed 4d ago), licensed MIT. It adds 51 tokens to every session and 2,651 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
great_cto
Use when the CTO describes a feature, task, or project goal. Orchestrates the full SDLC pipeline automatically based on project type.
opportunity-solution-tree
Build an Opportunity Solution Tree (OST) to structure product discovery — map a desired outcome to customer opportunities, possible solutions, and experiments. Based on Teresa Torres' Continuous Discovery Habits. Use when the team is unclear what to build next, when multiple opportunities compete, or before writing a…
done-blocked
Reusable reporting contract for any agent that hands work back to the pipeline. Forces ONE of two terminal statuses (DONE or BLOCKED) with a specific evidence shape. Stops vague "probably finished" and "kind of stuck" verdicts.
outcome-roadmap
Transform an output-focused roadmap (feature list) into an outcome-focused one. Rewrites initiatives as outcome statements reflecting user and business impact. Use when a roadmap lists features instead of results, when making a roadmap more strategic, or when communicating what success looks like vs what will be built.
pm-planning
Decomposition methodology for pm agent — turns an approved ARCH document into a Beads task list with explicit dependencies, time-boxes, and acceptance criteria. The pipeline can only orchestrate work it can see; this skill defines what "seeable work" looks like.
shipyard-executing-plans
Executes a written implementation plan with agents. Use when a written plan is ready to execute, in the current session or a separate one. Also use when the user says "build this", "implement this", "execute the plan", or "run the plan", or when a loaded plan file has independent tasks suitable for agent dispatch.