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 tomeraitz/claude-slack-bridge --skill build-process-skillgit clone --depth 1 https://github.com/tomeraitz/claude-slack-bridgeWrote 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/tomeraitz/claude-slack-bridge/build-process-skill)<a href="https://agentmods.dev/skills/tomeraitz/claude-slack-bridge/build-process-skill"><img src="https://agentmods.dev/badge/skills/tomeraitz/claude-slack-bridge/build-process-skill.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
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 →
- medium Agent Snooping · line 103 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.
- medium Agent Snooping · line 128 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 | $0.00120 | $0.03752 |
| Opus 5 | $0.00060 | $0.01876 |
| Sonnet 5 | $0.00024 | $0.00750 |
| Haiku 4.5 | $0.00012 | $0.00375 |
Grade A, and why
build-process-skill 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 8d 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
build-process-skill — write the /process orchestrator command
You run locally inside Claude Code (not via the Slack daemon). All clarifications go through AskUserQuestion. Do not call mcp__claude-slack-bridge__ask_on_slack from this skill — Slack is only the runtime channel for /process itself, not for setup.
This skill's only job is to create .claude/commands/process.md in the current repo. By the time it returns, either:
- The file has been written (status:
configured); or - The file already existed and the user chose to keep theirs (status:
skipped).
Return values the caller needs (printed as a fenced JSON block at the end of the final reply):
status—configuredorskipped.path—.claude/commands/process.mdwhen configured; omitted otherwise.
Step 1 — check whether .claude/commands/process.md already exists
If the file does not exist, continue to Step 2.
If it does exist, ask via AskUserQuestion:
.claude/commands/process.mdalready exists. Overwrite it with the standard scaffold?
Options:
-
No, keep mine — return immediately with
status: "skipped". Do not touch the file. -
Yes, overwrite — continue to Step 2.
-
No, create it under a different name — ask via
AskUserQuestion(free-text via "Other"):What filename should I use under
.claude/commands/? (e.g.process2.md,my-process.md— must end in.md)Validate the reply: it must end in
.md, contain no path separators, and not collide with an existing file in.claude/commands/. If invalid or colliding, re-ask. Once valid, record the chosen filename astarget_filenameand continue to Step 2 — substitute the chosen filename forprocess.mdeverywhere below, and update the frontmattername:to match (filename without.md).
Step 2 — write .claude/commands/process.md
Create .claude/commands/ if missing, then write process.md (atomic write: .process.md.tmp → os.replace) with the following scaffold:
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.
- 8d ago First seen · 220 lines · 120 tokens per session scan A 6d8ff3f92d17
build-process-skill is a skill published in the GitHub repository tomeraitz/claude-slack-bridge (33 stars, last pushed 18d ago), licensed MIT. It adds 120 tokens to every session and 3,752 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
slack-expert
Expert in Slack bot development, Block Kit UI, Events API, slash commands, OAuth flows, and app distribution. Use when the user mentions communication, collaboration, bots, API, Slack bot, or Block Kit, or when the task involves Slack Platform, Development Tools, Slack Bot with Bolt, or Python Slack Bot.
access
Manage Slack channel access — approve pairings, edit allowlists, set DM/channel policy. Use when the user asks to pair, approve someone, check who's allowed, or change policy for the Slack channel.
configure
Set up the Slack channel — save the bot and app tokens and review access policy. Use when the user pastes Slack tokens, asks to configure Slack, asks "how do I set this up" or "who can reach me," or wants to check channel status.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
simplify
Improve existing work with focused simplification passes across code, writing, research, operations, or general tasks.