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 TentacleOpera/switchboard --skill improve-featuregit clone --depth 1 https://github.com/TentacleOpera/switchboardWrote 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/tentacleopera/switchboard/improve-feature)<a href="https://agentmods.dev/skills/tentacleopera/switchboard/improve-feature"><img src="https://agentmods.dev/badge/skills/tentacleopera/switchboard/improve-feature/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/tentacleopera/switchboard/improve-feature"><img src="https://agentmods.dev/badge/skills/tentacleopera/switchboard/improve-feature.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Prompt Injection · line 5 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Excessive Agency · line 33 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00000 | $0.02090 |
| Opus 5.5 | $0.00000 | $0.00836 |
| Sonnet 5.5 | $0.00000 | $0.00418 |
| Haiku 4.5 | $0.00000 | $0.00209 |
Grade A, and why
improve-feature 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 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.
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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improve Feature
Use this workflow when the target is a Switchboard feature (a container of subtask plans), not a single plan. Its job is to make the subtask set coherent: improve every subtask, detect inconsistencies between them, and then restructure — merge overlapping plans, delete superseded ones, rewrite contradictory ones, split oversized ones.
Detect a feature when the target file is under .switchboard/features/, or contains an auto-generated <!-- BEGIN SUBTASKS ... --> / <!-- END SUBTASKS --> block. If the target is a single plan, use improve-plan instead.
Why this is a separate skill
improve-plan is deliberately non-destructive ("never delete content; only update the plan document") because for a single plan that is correct. For a feature it is the opposite of the job — the highest-value action is exactly the thing improve-plan forbids: recognising that two plans are one, that a plan is obsolete, or that a contradiction means one plan gets rewritten. This skill is authorised to cut. Invoking it is the sign-off to restructure the subtask set; there is no per-run confirmation gate.
Guardrails (different from improve-plan, not fewer)
Restructuring is expected — but bounded:
- Preserve information, not files. Every requirement, edge case, and root-cause note from a plan you delete or merge MUST survive in its target plan. The unit of preservation is the union of intent across the set, never each individual
.md. - Git is the undo. Commit before any destructive op (delete/merge) so it is trivially reversible. Deletion of a plan file on a branch is cheap — it is a working document, not shipped user data. Do not treat it with production-data caution.
- Never hand-edit the auto-generated subtasks block (
<!-- BEGIN/END SUBTASKS -->) — Switchboard regenerates it from the DB. - Route set changes through the real mechanisms, not the block:
- Remote (no extension):
git rmthe removed subtask.mdfiles (the plan watcher hard-deletes their rows on the next local pull), create any new consolidated plan file (do NOT write a**Plan ID:**line — it is never read; the importer assigns the ID and keys by file path), and add a**Feature:** <feature-plan-id>line to the new plan file's frontmatter (the feature's UUID, taken from itsfeature-<uuid>.mdfilename; applied on import with apply-if-empty semantics). For column moves, you MUST move newly created cards toPLAN REVIEWEDusing the session-appropriate mechanism:- Local (extension or standalone host running): Use the
kanban_operationsskill (move-card.js) or CLI (switchboard api POST /kanban/move) to move the card toPLAN REVIEWED. - Remote (no extension): Use the Notion/Linear provider or MCP to move the card to
PLAN REVIEWED. In-place rewrites keep their existing column.
- Local (extension or standalone host running): Use the
- Local (extension running): use
assign-to-feature.js/ the feature's create path for card-set changes.
- Remote (no extension):
- Report the restructure — what merged into what, what was deleted, what survived — so the diff is legible. End with the reconciled subtask list.
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 Changed · -1 lines 3e2ca120aaa2
- 1mo ago First seen · 76 lines · 0 tokens per session scan A 75c7c779a089
improve-feature is a skill published in the GitHub repository TentacleOpera/switchboard (215 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,090 tokens. 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 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…