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 agentmods add skills/tentacleopera/switchboard/improve-featurenpx 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.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 | $0.00000 | $0.02218 |
| Opus 5 | $0.00000 | $0.01109 |
| Sonnet 5 | $0.00000 | $0.00444 |
| Haiku 4.5 | $0.00000 | $0.00222 |
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 4d 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 — 76 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:
- If SWITCHBOARD STATUS: Live is present in your prompt, you are local — use the injected port for kanban_operations calls; skip the .switchboard/api-server-port.txt file-existence detection.
- 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 running —
.switchboard/api-server-port.txtpresent orSWITCHBOARD STATUS: Livein prompt): Use thekanban_operationsskill (move-card.js) to move the card toPLAN REVIEWED. (IfSWITCHBOARD STATUS: Liveis present, you are local — use the injected port directly forkanban_operationscalls and skip.switchboard/api-server-port.txtfile-existence detection.) - Remote (no extension —
.switchboard/api-server-port.txtabsent and noSWITCHBOARD STATUS: Liveline): Use the Notion/Linear provider or MCP to move the card toPLAN REVIEWED. In-place rewrites keep their existing column. Detect remote by the absence of.switchboard/api-server-port.txt.
- Local (extension running —
- Local (extension running): use
assign-to-feature.js/ the feature's create path for card-set changes.
- 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.
- 4d ago First seen · 76 lines · 0 tokens per session scan A 75c7c779a089
improve-feature is a skill published in the GitHub repository TentacleOpera/switchboard (213 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,218 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…