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 mskadu/opencode-agent-skills --skill skill-suggestergit clone --depth 1 https://github.com/mskadu/opencode-agent-skillsWrote 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/mskadu/opencode-agent-skills/skill-suggester)<a href="https://agentmods.dev/skills/mskadu/opencode-agent-skills/skill-suggester"><img src="https://agentmods.dev/badge/skills/mskadu/opencode-agent-skills/skill-suggester.svg" alt="Measured on agentmods" 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 | $0.00022 | $0.00490 |
| Opus 5 | $0.00011 | $0.00245 |
| Sonnet 5 | $0.00004 | $0.00098 |
| Haiku 4.5 | $0.00002 | $0.00049 |
Grade A, and why
skill-suggester 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 6d 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.
What it actually says
What I do
Reads your opencode prompt history, finds repeated multi-step workflows, and recommends skill-worthy candidates. Saves you from having the same conversation twice.
How to invoke
Run /skill skill-suggester to scan the full history. Optionally pass --since <date> (e.g. --since 2026-05-01) to limit the window.
Analysis method
- Locate prompt history files at
~/.local/state/opencode/prompt-history*.jsonl - Parse each entry's message content
- Score for skill potential by looking for:
- Repetition: similar phrasing or topic used 3+ times ("scan all repos", "check my inbox")
- Multi-step sequences: a request that required 5+ tool calls to complete
- Unsupported requests: things you asked for that don't have a dedicated skill yet
- Workaround patterns: instructions you give every time instead of a one-shot command
- For each candidate, note:
- How many times the pattern appeared
- How many tool calls it consumed
- The estimated time savings if it were a skill
Output format
## Skill Candidates (last N entries)
### 1. "<candidate name>" (PRIORITY)
- **Pattern**: <what you keep asking for>
- **Frequency**: X times in history
- **Avg complexity**: Y tool calls per instance
- **Estimated savings**: ~Z minutes/week
- **Evidence**:
- "[excerpt from prompt history]"
- "[another excerpt]"
- **Recommendation**: <create as skill | add as command template | not worth it>
### 2. ...
Key rules
- Only flag patterns that happen more than twice. One-offs are not skills.
- Include direct quotes from your past prompts as evidence.
- Rate each candidate:
high(clear ROI, use weekly),medium(nice to have),low(rare but worth noting). - If nothing qualifies, say so and explain why.
- After presenting candidates, ask if you want to create any of them.
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.
- 6d ago First seen · 55 lines · 22 tokens per session scan A e31f8ad824f2
skill-suggester is a skill published in the GitHub repository mskadu/opencode-agent-skills (1 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 490 once invoked, about $0.0001 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
architecture-diagram
Build interactive, click-through architecture diagrams for software systems — a self-contained single HTML file with animated step-by-step flows, mode toggles (dev/prod, offline/online, v1/v2), dark/light theme, and a side panel with payload details, plus a companion markdown description. Use when the user wants to…
rigorous-review
Rigorous, evidence-backed code review for high-stakes changes. Trigger on: rigorous review, thorough review, deep review, review this PR properly, review before merge, high-stakes review, "is this actually safe to merge", regulated or compliance code review, batch-review these PRs. Every finding carries quoted…
alloy-structural-analysis
Formal model-checking layer over Allium specs using Alloy 6 + Electrod + nuXmv. Trigger on: "rigorous structural analysis", "model-check this spec", "verify this Allium spec formally", "check for structural divergence with Alloy", "run the Alloy loop", "does the code actually satisfy this spec", temporal/CTL/LTL…
daily-briefing
Daily orientation and chief-of-staff briefing. Pulls from Slack (saved items), Gmail (important/starred), Google Calendar (today's events), Jira CLI (configured projects), and Todoist CLI, validates every action item, synthesizes a prioritized briefing using three consequence-based tiers, then produces a decisive…
jira
Manage Jira issues, sprints, and epics with the jira CLI (ankitpokhrel/jira-cli). Trigger on: jira, jira-cli, ticket, issue key (e.g. PROJ-123), epic, sprint, transition/move ticket, comment on ticket, assign ticket, JQL, create bug/story, "what's on my board", "my open issues". Use when the user wants to find, read…
scala
Enforces required tool order for Scala/Java projects. Compile/test: use the bloop CLI directly (bloop compile, bloop test) — never sbt compile/sbt test. Search/navigate: scalex first, then ast-grep, then a semantic/LSP-aware tool if one is available, then grep/ripgrep as last resort — this order is unconditional, even…