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/psd401/psd-claude-pluginsnpx agentmods add skills/psd401/psd-claude-plugins/class-intercomWrote 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/psd401/psd-claude-plugins/class-intercom)<a href="https://agentmods.dev/skills/psd401/psd-claude-plugins/class-intercom"><img src="https://agentmods.dev/badge/skills/psd401/psd-claude-plugins/class-intercom/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/psd401/psd-claude-plugins/class-intercom"><img src="https://agentmods.dev/badge/skills/psd401/psd-claude-plugins/class-intercom.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 | $0.00131 | $0.01347 |
| Opus 5.5 | $0.00052 | $0.00539 |
| Sonnet 5.5 | $0.00026 | $0.00269 |
| Haiku 4.5 | $0.00013 | $0.00135 |
Grade A, and why
class-intercom scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 14d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Class Intercom CLI
A self-contained CLI for Peninsula School District's Class Intercom (social media / school comms platform), generated with Printing Press from the live web app and hand-extended for PSD. Read-focused (content feed, channels, social feed, moderation, reports, tasks); the only write is create-draft, which can only create an unsent draft.
Built for PSD's Class Intercom workspace. Auth is your own browser session, so it works for whatever the authenticated account can access.
Setup (one-time)
1. Resolve the binary
The binary is not committed to the repo. Resolve it once — this downloads the prebuilt binary for your platform from the repo's GitHub Release (or builds it from cli/ if you have Go and no network):
BIN="$(bash scripts/ensure-binary.sh)" # run from this skill's directory
"$BIN" --version
Use "$BIN" for every command below. It caches under ~/.cache/classintercom-pp-cli/, so this is a one-time cost.
2. Authenticate (Chrome cookie)
Auth is a Class Intercom session cookie read from Chrome. Install the cookie extractor once, then log in:
uv tool install pycookiecheat # one-time; the CLI shells out to it
# Be logged into app.classintercom.com in Chrome, then:
"$BIN" auth login --chrome # approve the macOS Keychain prompt if shown
"$BIN" auth status # should print "Authenticated"
Re-run auth login --chrome if the session expires.
Global flags
Every command supports --json, --csv, --compact, --agent (all agent-friendly defaults), --dry-run, and --select <fields>. Framework commands sync (mirror to local SQLite), search, and api (browse all endpoints) are also available.
Read commands
Channels
"$BIN" channels --json # social channels with their UUIDs (value), network, label
The value field is the channel UUID you pass to create-draft --channel.
Content / activities (content <cmd>)
What ships with it
60 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.
- cli/.golangci.yml 147 B
- cli/.goreleaser.yaml 1.3 KB
- cli/AGENTS.md 2.4 KB
- cli/CHANGELOG.md 133 B
- cli/cmd/classintercom-pp-cli/main.go 343 B
- cli/cmd/classintercom-pp-mcp/main.go 2.1 KB
- cli/go.mod 1.7 KB
- cli/go.sum 10 KB
- cli/internal/cache/cache.go 1.7 KB
- cli/internal/cli/agent_context.go 7.9 KB
- cli/internal/cli/api_discovery.go 3.6 KB
- cli/internal/cli/auth.go 51 KB
- cli/internal/cli/channel_workflow.go 4.8 KB
- cli/internal/cli/content_list_content.go 3.5 KB
- cli/internal/cli/content_list_failed_count.go 3.1 KB
- cli/internal/cli/content_list_filters_config.go 3.6 KB
- cli/internal/cli/content_list_holidays.go 3.3 KB
- cli/internal/cli/content_list_tasks.go 3.3 KB
- cli/internal/cli/content.go 787 B
- cli/internal/cli/create_draft.go 6.0 KB
- cli/internal/cli/data_source.go 22 KB
- cli/internal/cli/deliver.go 3.5 KB
- cli/internal/cli/doctor.go 23 KB
- cli/internal/cli/feedback.go 6.6 KB
- cli/internal/cli/helpers.go 56 KB
- cli/internal/cli/import.go 2.9 KB
- cli/internal/cli/libraries_list_filters_config.go 3.3 KB
- cli/internal/cli/libraries_list_libraries.go 3.7 KB
- cli/internal/cli/libraries.go 649 B
- cli/internal/cli/moderation_list_filters_config.go 3.6 KB
- cli/internal/cli/moderation_list_moderation.go 3.7 KB
- cli/internal/cli/moderation.go 655 B
- cli/internal/cli/profile.go 10 KB
- cli/internal/cli/promoted_binder.go 3.3 KB
- cli/internal/cli/promoted_channels.go 3.1 KB
- cli/internal/cli/reports_list_filters_config.go 4.3 KB
- cli/internal/cli/reports_list_reports.go 3.5 KB
- cli/internal/cli/reports.go 637 B
- cli/internal/cli/root_test.go 8.3 KB
- cli/internal/cli/root.go 11 KB
- cli/internal/cli/search.go 8.2 KB
- cli/internal/cli/social_list_feed.go 3.2 KB
- cli/internal/cli/social_list_filters_config.go 3.5 KB
- cli/internal/cli/social.go 629 B
- cli/internal/cli/sync_hint_test.go 5.2 KB
- cli/internal/cli/sync_hint.go 3.2 KB
- cli/internal/cli/sync_numeric_id_test.go 1.3 KB
- cli/internal/cli/sync.go 59 KB
- cli/internal/cli/tasks_list_assignables.go 3.1 KB
- cli/internal/cli/tasks_list_filters_config.go 3.4 KB
- cli/internal/cli/tasks_list_tasks.go 3.5 KB
- cli/internal/cli/tasks.go 676 B
- cli/internal/cli/version.go 725 B
- cli/internal/cli/which_test.go 3.8 KB
- cli/internal/cli/which.go 8.7 KB
- cli/internal/client/client_test.go 2.0 KB
- cli/internal/client/client_verify_short_circuit_test.go 6.2 KB
- cli/internal/client/client.go 32 KB
- cli/internal/cliutil/cliutil_test.go 26 KB
- cli/internal/cliutil/duration_test.go 1.6 KB
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.
- 14d ago Changed · -1 lines 776ddb2bf7a9
- 1mo ago Changed f255f722bacb
- 2mo ago First seen · 111 lines · 131 tokens per session scan A d554aae6a9cd
class-intercom is a skill published in the GitHub repository psd401/psd-claude-plugins (2 stars, last pushed 9d ago), licensed MIT. It adds 131 tokens to every session and 1,347 once invoked, about $0.0005 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 2026-08-31.
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…