Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/TentacleOpera/switchboardnpx agentmods add skills/tentacleopera/switchboard/manage-featuresWrote 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/manage-features)<a href="https://agentmods.dev/skills/tentacleopera/switchboard/manage-features"><img src="https://agentmods.dev/badge/skills/tentacleopera/switchboard/manage-features/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/manage-features"><img src="https://agentmods.dev/badge/skills/tentacleopera/switchboard/manage-features.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 8 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 62 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.
- high Prompt Injection · line 239 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.
- high Prompt Injection · line 290 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.
- high Prompt Injection · line 447 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.
- high Prompt Injection · line 447 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.
- high Tool Misuse · line 454 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Rogue Agent · line 462 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium Agent Snooping · line 404 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 | $0.00060 | $0.06844 |
| Opus 5.5 | $0.00024 | $0.02738 |
| Sonnet 5.5 | $0.00012 | $0.01369 |
| Haiku 4.5 | $0.00006 | $0.00684 |
Grade A, and why
manage-features 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 — 505 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manage Features
Create, group, and rearrange Switchboard features. This skill consolidates four feature-management operations into one discoverable skill:
- Create — write a feature file directly (remote-session fallback when the extension is not running).
- Create from Plans — create a feature from a known set of plans via
create-feature.js(extension running). - Group — scan pre-coding columns, cluster loose plans by capability, propose groupings for one approval, then create features.
- Rearrange — restructure a feature's subtasks (split/move/merge/reorder) without rewriting their content.
When a directive says "invoke the manage-features skill and follow the
Create from Plans section", jump to that section below.
Create
Create a Switchboard feature by writing the feature file directly to
.switchboard/features/. Use this section when you are in a remote session
(Claude Code web, claude.ai) and the VS Code extension is not running —
create-feature.js routes through the extension's LocalApiServer and has no
direct-DB fallback, so it fails when the extension is unreachable.
When to Use
- You are in a remote session (no VS Code extension running).
- The user asks to create a new feature (grouping plans together, or a standalone feature).
- Do NOT use this section if the extension IS running — call
create-feature.jsinstead (it's authoritative: does DB upsert, subtask linking, file write, and board refresh atomically).
How to Detect Whether the Extension Is Running
- Run
switchboard api GET /health. - If it responds with status
ok, Switchboard is live — usecreate-feature.js. - If it fails or is offline, proceed with direct file write.
Feature File Format
Feature files live in .switchboard/features/ and follow this structure:
---
description: '{Feature Name}'
---
# {Feature Name}
## Goal
{Description of what this feature achieves and why it matters.}
## How the Subtasks Achieve This
{Narrative connecting the subtasks to the goal. Written once by the agent;
preserved by _regenerateFeatureFile on subsequent subtask changes.}
<!-- BEGIN SUBTASKS (auto-generated, do not edit) -->
## Subtasks
- [ ] (no subtasks)
<!-- END SUBTASKS -->
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 · +6 lines · +60 tokens per session d80a13a8b2d4
- 1mo ago Changed · +17 lines 4022562cb56b
- 1mo ago Changed · -4 lines fe27e7af01a4
- 1mo ago First seen · 486 lines · 0 tokens per session scan A 4b8771e5d561
manage-features is a skill published in the GitHub repository TentacleOpera/switchboard (215 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 6,844 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
remove
Remove a deployed framework or addon from the current workspace.