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 bonnguyenitc/specship --skill ss-specgit clone --depth 1 https://github.com/bonnguyenitc/specshipWrote 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/bonnguyenitc/specship/ss-spec)<a href="https://agentmods.dev/skills/bonnguyenitc/specship/ss-spec"><img src="https://agentmods.dev/badge/skills/bonnguyenitc/specship/ss-spec/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/bonnguyenitc/specship/ss-spec"><img src="https://agentmods.dev/badge/skills/bonnguyenitc/specship/ss-spec.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 | $0.00080 | $0.02795 |
| Opus 5 | $0.00040 | $0.01398 |
| Sonnet 5 | $0.00016 | $0.00559 |
| Haiku 4.5 | $0.00008 | $0.00280 |
Grade A, and why
ss-spec 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 9d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec
Goal: turn a spec into a precise, shared understanding before designing or coding. Most implementation bugs are misunderstood requirements — catch them here.
When to use
- You're handed a ticket / PRD / feature request to build.
- Requirements are ambiguous and you need to pin them down before acting.
- First stage of the workflow: spec → plan → coding → review (+
debug).
Shared task state
Part of the task pipeline — see ../WORKFLOW.md for the full contract. This skill opens the task.
- Hydrate: if continuing an existing task, read
tasks/TASK-<ID>/task.md+spec.md; otherwise pick a newTASK-<ID>and create the folder. Readdocs/onboarding/*if present; if those docs are missing and the codebase is unfamiliar, offer to runss-explore-sourcefirst — its output is the convention reference for every later stage. - Checkpoint: create/update
task.md(the shared state file) alongsidespec.md— setstage: spec,specartifact statusdraft→confirmed, bumpupdated:, append a Pipeline Log line carrying your agent label (format:../WORKFLOW.md→ Agent handoff). - Blocked? If the spec can't be confirmed because a blocker
Q#is waiting on the user or an external answer, setstatus: blocked, note it in the Now block'sBlocked by:line, and log it; flip back toactiveonce it's answered.blockedis involuntary — to set the task aside by choice, usess-pause-task. See../WORKFLOW.md→ Status values. - Lessons: read
tasks/LESSONS.mdat hydrate and apply its rules; if you detect a process mistake, fix it and append anL#entry there (see../WORKFLOW.md→ Lessons).
Method
1. Read the source completely
- Read the full spec/ticket and any linked docs, designs, or related issues.
- Ground it in the actual code, not memory. If the spec references code areas, open them: verify the named files/functions/flags exist, and record the current behavior vs. desired behavior delta — requirements stated against imagined code are the top source of misunderstood specs. Use the
ss-explore-sourceskill if the project is unfamiliar. - Delegate heavy exploration to a subagent. When grounding the spec means sweeping a large or unfamiliar codebase (broad "where is X handled?" questions, many candidate files), spawn the
ss-exploreragent if your platform can spawn it (ships with specship for Claude Code), else the built-in Explore agent, with a focused brief and ask for structured conclusions, not file dumps - it keeps this thread's context clean for the spec itself. Verify any path or symbol an agent reports before citing it inspec.md. For a small, known area, just read inline — and if your platform can't spawn subagents at all, do the exploration inline too (../WORKFLOW.md→ In-stage subagents: delegation is an optimization, never a precondition).
What ships with it
1 file 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.
- 9d ago First seen · 124 lines · 80 tokens per session scan A 63185ddb0b2c
ss-spec is a skill published in the GitHub repository bonnguyenitc/specship (2 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 2,795 once invoked, about $0.0004 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
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
html-artifacts
Author the HTML for a plan artifact, dashboard iframe, or Slack attachment — structure, design plan, available runtime, theming, and craft. Read this before writing HTML for saveplan, outputiframe, or slackattachhtml.
design-taste-frontend-v1
The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is design-taste-frontend (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.
brandkit
Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional…
redesign-existing-projects
Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.
gpt-taste
Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.