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 ailiheizi/workflow-to-skill --skill dsh-model-signal-radargit clone --depth 1 https://github.com/ailiheizi/workflow-to-skillWrote 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/ailiheizi/workflow-to-skill/dsh-model-signal-radar)<a href="https://agentmods.dev/skills/ailiheizi/workflow-to-skill/dsh-model-signal-radar"><img src="https://agentmods.dev/badge/skills/ailiheizi/workflow-to-skill/dsh-model-signal-radar/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/ailiheizi/workflow-to-skill/dsh-model-signal-radar"><img src="https://agentmods.dev/badge/skills/ailiheizi/workflow-to-skill/dsh-model-signal-radar.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 | $0.00119 | $0.02206 |
| Opus 5.5 | $0.00048 | $0.00882 |
| Sonnet 5.5 | $0.00024 | $0.00441 |
| Haiku 4.5 | $0.00012 | $0.00221 |
Grade A, and why
dsh-model-signal-radar scanned grade A 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **`bash` tool with the `curl` CLI** — `/usr/bin/curl 8.7.1` verified present How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model Signal Radar
Produce one concise, evidence-backed signal (or up to max signals) about a
recent AI model or developer-platform change, sourced only from official
vendor pages, with announcement clearly separated from actual availability.
The Skill is read-only: it never subscribes, publishes, modifies accounts, or
performs any recommended follow-up action.
Target harness: DSH headless profile (operator-identified as DSH 0.1.0-rc.7). The exact tool bindings below were observed in a live headless run on 2026-08-25; reuse on another harness requires re-confirming equivalent bindings, parameters, and network reachability.
Goal And Inputs
Outcome. For a given focus, report the most relevant recent change from official sources, each signal stating: what changed, the official URL where it was observed, the date observed on that URL, the availability state, and the verified/unverified boundary. Output is readable Markdown in the user's language.
Scope. AI model changes (weights, API, product releases, deprecations) and developer-platform changes (API/CLI/SDK releases, pricing, feature announcements) from official vendor sources. Excluded: general tech news, opinion/rumor, community speculation, market analysis, and anything behind a login or paywall.
Completion criteria (Must). Every included signal has all five of:
- an observed official URL fetched directly (HTTP response seen, not just cited);
- a date observed on that official URL;
- an availability state with the quoted evidence it rests on;
- an explicit verified/unverified boundary;
- a truthful source-health summary (per-source outcome, partial coverage).
Runtime inputs.
| Input | Required | Default | Meaning / validation |
|---|---|---|---|
focus |
yes | — | Topic keyword or phrase (vendor, model family, platform). Non-empty. |
time window |
no | previous 14 days | Relative ("14d", "30d") or explicit dates; interpret relative to the current date. |
max signals |
no | 3 | Positive integer; the cap on returned signals. |
source policy |
no | official-only | official-only or official-first; never lowers the evidence bar. |
| language | no | user's language | Output language; follow the user's request. |
What ships with it
7 files 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 · 172 lines · 119 tokens per session scan A 0c64b28aa298
dsh-model-signal-radar is a skill published in the GitHub repository ailiheizi/workflow-to-skill (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 119 tokens to every session and 2,206 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-16.
Other skills, from other repositories
dspy-prompt-optimizer
Tunes prompts iteratively using reflection and success metrics. Use for: optimize this prompt, dspy tune, improve prompt with reflection, self-refine-loop.
knowledge-graph-builder
Builds structured knowledge graphs from text and sessions. Use for: knowledge graph, map entities, build graph, entity map.
ai-engineering-toolkit
Overview of six AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
guidance
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework.
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
sdlc-accelerate
End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions.