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 ambient-code/platform --skill discovergit clone --depth 1 https://github.com/ambient-code/platformWrote 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/ambient-code/platform/discover)<a href="https://agentmods.dev/skills/ambient-code/platform/discover"><img src="https://agentmods.dev/badge/skills/ambient-code/platform/discover/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/ambient-code/platform/discover"><img src="https://agentmods.dev/badge/skills/ambient-code/platform/discover.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 Agent Snooping · line 57 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00064 | $0.00693 |
| Opus 5.5 | $0.00026 | $0.00277 |
| Sonnet 5.5 | $0.00013 | $0.00139 |
| Haiku 4.5 | $0.00006 | $0.00069 |
Grade B, and why
discover scanned grade B with 1 finding 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls .claude/skills/ 2>/dev/null How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discover Domain Skills
Before writing or changing anything, discover what skills and context are available for the domains you're about to work in.
When to Use
Every time. This skill is the entry point for all coding and spec work. Do not skip it, even for one-line fixes.
User Input
$ARGUMENTS
If provided, use the input to narrow which domains to check. Otherwise, infer from the task context.
Steps
1. Identify Relevant Domains
Map the work to one or more capability domains:
| Domain | When working on |
|---|---|
sessions |
Session lifecycle, data model, API resources, messages, events |
control-plane |
Operator, reconciliation, scheduling, runner provisioning |
agents |
Agent model, runner, runtime registry, prompts |
integrations |
MCP server, Gerrit, external services, feature flags |
frontend |
UI components, pages, React Query hooks |
auth |
OAuth, credentials, RBAC, tokens |
projects |
Project management, settings, workspaces |
cli |
TUI, acpctl commands |
specs |
specs |
If unsure, check which specs/ subdirectories exist:
ls -d specs/*/
2. Visit Each Domain
For every relevant domain, cd into its spec directory and list available skills:
cd specs/{domain}
ls .claude/skills/ 2>/dev/null
ls skills/ 2>/dev/null
Read the SKILL.md of any discovered skill that looks relevant to the task at hand.
3. Load Domain Specs
While in the domain directory, check for specs that describe the desired state of what you're about to change:
ls *.spec.md 2>/dev/null
Read the relevant spec before implementing — code reconciles against specs, not the other way around.
4. Check Deployment Skills
If the work involves deployment, manifests, Docker builds, or cluster operations, check for deployment skills:
ls skills/deployments/ 2>/dev/null
Read the relevant SKILL.md — these contain environment config, prerequisites, and troubleshooting for deploying each component.
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.
- 1mo ago First seen · 105 lines · 64 tokens per session scan B 4ea51c3a6f28
discover is a skill published in the GitHub repository ambient-code/platform (131 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 693 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
argent-tv-interact
Control and inspect TV apps via argent, Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…
Swift Performance Optimization Skill
Use when investigating measured Swift or Apple-platform regressions in CPU, memory, launch, scrolling, animation hitches, image processing, energy, networking, or concurrency, or when designing performance tests and Instruments experiments. Do not use for speculative micro-optimization, ordinary refactoring, or a…
06-product-brief
Produces a concise Product Brief before requirements. Use when the user wants to frame or revisit a product opportunity and how it will be validated. Not for requirements, technical design, or planning.
issue-resolve
Use when an assessed gflow-cli issue (verdict CONFIRMED-BUG or LIKELY-BUG) has localized, verifiable scope and should be driven to a fix. Mutating and gated: it works in an isolated worktree, fixes test-first, and opens a DRAFT PR for human review. Built to run autonomously (hermes-ops) within a strict action envelope…
10-todo
Split the user prompt into independent todos and run one executor agent per todo in parallel, then report a minimal table. Use when the user says "todo" or asks to fan out a multi-part request into parallel implementations.
conversational-ux
Design voice and conversational interfaces — dialog flows, error recovery, and persona. Use when the interface speaks and listens rather than being tapped. For graphical input collection, use form-design.