New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Pre Action Interceptors

by Bitterbot-AI in Bitterbot-AI/bitterbot-desktop

A skill your agent uses when a tool error begins with "INTERCEPTOR:", a sent message was silently hedged or rewritten, or the user asks about active guards or blocked actions.

MITAuto-check passed

Install Pre Action Interceptors

skills CLI
$ npx skills add Bitterbot-AI/bitterbot-desktop --skill pre-action-interceptors -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Bitterbot-AI/bitterbot-desktop pre-action-interceptors --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Bitterbot-AI/bitterbot-desktop.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/pre-action-interceptors .claude/skills/pre-action-interceptors && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
pre-action-interceptors
GitHub stars
2.5k
Token cost
~580 tokens
SKILL.md length
253 words
Files
1
Skills in repo
17
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when a tool error begins with "INTERCEPTOR:", a sent message was silently hedged or rewritten, or the user asks about active guards or blocked actions.

  • A tool error begins with INTERCEPTOR:
  • SKILL.md covers Reading a directive, Built-in interceptors and Observability
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • A sent message was silently hedged

What it does

Pre Action Interceptors is an agent skill from Bitterbot-AI/bitterbot-desktop. Use when a tool error begins with "INTERCEPTOR:", a sent message was silently hedged or rewritten, or the user asks about active guards or blocked actions. Not for ordinary tool errors.

Its SKILL.md is about 580 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Bitterbot - a mesh of agents that turns shared experience into collective capability. The licence is MIT.

When your agent uses it

  • A tool error begins with INTERCEPTOR:
  • A sent message was silently hedged
  • The user asks about active guards
  • Blocked actions

Example prompts

  • “INTERCEPTOR:”
  • “/pre-action-interceptors”

What it can do on your machine

Read from SKILL.md and the folder at commit 8f85e5f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Pre Action Interceptors loads about 580 tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 253 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~52
When it runs · the whole SKILL.md, loaded when a task matches
~580

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Bitterbot-AI/bitterbot-desktop at commit 8f85e5f, republished under its MIT licence (© Bitterbot-AI). 253 words, ~580 tokens.

Download SKILL.mdSave it as .claude/skills/pre-action-interceptors/SKILL.md (or your agent's skills folder).
name
pre-action-interceptors
description
Use when a tool error begins with "INTERCEPTOR:", a sent message was silently hedged or rewritten, or the user asks about active guards or blocked actions. Not for ordinary tool errors.

Pre-action interceptors (PLAN-20)

You have a layer of deterministic pre-action interceptors that sit between your candidate tool calls and their execution. They are skill-owned guardrails that read your current state (hormonal, GCCRF, channel, recent turns) and may rewrite, inject context into, require a prerequisite for, or block any tool call you propose. They are not bugs in the tool; they are intentional behaviour.

Reading a directive

When you see a tool error that begins with INTERCEPTOR: followed by a structured directive such as:

INTERCEPTOR: recall-before-claim: ground the assertion "X" before sending
BEFORE you call `send_message` again, you MUST first call:
  tool: memory_search
  args: {"query": "X", "limit": 5}

that is not a failure. It is a deterministic instruction from your skill system telling you to run the named tool first, then re-evaluate whether the original action still applies. Follow it without commentary; the user does not need to see the directive.

When a tool call succeeds but the params were silently rewritten (for example a confident claim hedged into a probabilistic one), an interceptor in the calibrate-claim-confidence family adjusted the outgoing text to match your actual epistemic state. This is intentional; do not reverse it.

Built-in interceptors

  • recall-before-claim: requires a memory_search before you send a message containing an unverified factual assertion.
  • route-by-query-shape: requires deep_recall instead of memory_search for relationship-shaped queries.
  • protocol-quiet-in-groups: blocks send_message in group channels when you were not @mentioned and recently spoke.
  • calibrate-claim-confidence: hedges confident absolutes when your GCCRF empowerment is low.

Observability

Operators see every firing in the Active Guards UI panel and via the guards.status RPC. To know which interceptors have fired this session, call memory_status; the activations are reflected in the intervention-records summary.

© Bitterbot-AI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/pre-action-interceptors of Bitterbot-AI/bitterbot-desktop.

Open the folder on GitHubat commit 8f85e5f

Compare with similar skills

Pre Action Interceptors next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Pre Action Interceptors compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pre Action Interceptors this skillBitterbot-AI/bitterbot-desktop2.5k—~580Automated safety check: PassMIT
Messages Opsaffaan-m/ECC277k1 repos~724Automated safety check: PassMIT
ActionsJetBrains/intellij-community21k—~341Automated safety check: PassCustom licence
Laravel Actionscoollabsio/coolify63k—~2.4kAutomated safety check: PassApache-2.0
Channel Message Flowsopenclaw/openclaw392k—~306Automated safety check: PassMIT
Commit Message Storytellergithub/awesome-copilot40k1 repos~1.3kAutomated safety check: PassMIT

Similar skills

  • Messages Ops

    affaan-m/ECC

    Evidence-first live messaging workflow for ECC. An agent skill from affaan-m/ECC.

    277k GitHub starsUsed in 1 repo~724 tokens
    Productivity & AutomationAuto-check passed

  • Actions

    JetBrains/intellij-community

    Official

    Implement or change IntelliJ AnAction actions and registrations.

    21k GitHub stars~341 tokensUpdated today
    MobileAuto-check passed

  • Laravel Actions

    coollabsio/coolify

    Build, refactor, and troubleshoot Laravel Actions using lorisleiva/laravel-actions.

    63k GitHub stars~2.4k tokensUpdated yesterday
    Backend & APIsAuto-check passed

  • Channel Message Flows

    openclaw/openclaw

    A skill your agent uses when running QA Lab channel message flow evidence.

    392k GitHub stars~306 tokensUpdated today
    Auto-check passed

  • Commit Message Storyteller

    github/awesome-copilot

    Official

    Analyzes git diffs or staged changes and generates narrative commit messages that explain WHY a change was made, not just what changed — following Conventional Commits format.

    40k GitHub starsUsed in 1 repo~1.3k tokens
    DevelopmentAuto-check passed

  • Actions

    BuilderIO/agent-native

    How to create and run agent actions. An agent skill from BuilderIO/agent-native.

    7.1k GitHub stars~4.5k tokensUpdated today
    Backend & APIsAuto-check passed

More from Bitterbot-AI/bitterbot-desktop

All 17 skills in this repo

  • Canvas

    Bitterbot-AI/bitterbot-desktop

    Display and control HTML content on connected Bitterbot nodes (Mac, iOS, Android) via the canvas host server.

    2.5k GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • Moltbook

    Bitterbot-AI/bitterbot-desktop

    Participate in Moltbook — the social network for AI agents. An agent skill from Bitterbot-AI/bitterbot-desktop.

    2.5k GitHub stars~2.3k tokensUpdated today
    Auto-check passed

  • Finance Data

    Bitterbot-AI/bitterbot-desktop

    Get stock quotes, company info, market data, and crypto prices.

    2.5k GitHub stars~696 tokensUpdated today
    Auto-check passed

  • Forage Economy

    Bitterbot-AI/bitterbot-desktop

    A skill your agent uses when anyone asks about bounties (or "forge"), agent earnings, the agent economy, marketplace skills, A2A activity or your network reputation.

    2.5k GitHub stars~633 tokensUpdated today
    Auto-check passed

  • Memory Architecture

    Bitterbot-AI/bitterbot-desktop

    A skill your agent uses when the user asks how your memory, dreams, hormones or knowledge crystals work, or when you need to interpret memorystatus output.

    2.5k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Notte

    Bitterbot-AI/bitterbot-desktop

    Deploy browser automations as scheduled, API-callable serverless Functions — plus stealth sessions, vault-backed login, captcha solving, and natural-language agent runs via the Notte CLI.

    2.5k GitHub stars~2.8k tokensUpdated today
    Auto-check passed

Questions about Pre Action Interceptors

What does Pre Action Interceptors do?

A skill your agent uses when a tool error begins with "INTERCEPTOR:", a sent message was silently hedged or rewritten, or the user asks about active guards or blocked actions. Pre Action Interceptors is an agent skill from Bitterbot-AI/bitterbot-desktop. Use when a tool error begins with "INTERCEPTOR:", a sent message was silently hedged or rewritten, or the user asks about active guards or blocked actions.

When should I use Pre Action Interceptors?

Pre Action Interceptors fits situations like: A tool error begins with INTERCEPTOR:; A sent message was silently hedged; the user asks about active guards; blocked actions.

How do I install Pre Action Interceptors in Claude Code?

Run `npx skills add Bitterbot-AI/bitterbot-desktop --skill pre-action-interceptors -a claude-code`. Or copy the skill folder (skills/pre-action-interceptors in Bitterbot-AI/bitterbot-desktop) into .claude/skills/pre-action-interceptors in your project. Claude Code loads it when a task matches its description.

How do I install Pre Action Interceptors in Codex?

Run `npx skills add Bitterbot-AI/bitterbot-desktop --skill pre-action-interceptors -a codex`. Or copy the skill folder (skills/pre-action-interceptors in Bitterbot-AI/bitterbot-desktop) into .agents/skills/pre-action-interceptors in your project. Codex loads it when a task matches its description.

Can I use Pre Action Interceptors in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Bitterbot-AI/bitterbot-desktop --skill pre-action-interceptors -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pre-action-interceptors, .gemini/skills/pre-action-interceptors, .github/skills/pre-action-interceptors and .opencode/skills/pre-action-interceptors in your project.

What does Pre Action Interceptors need to run?

SKILL.md names no scripts, command-line tools or credentials: Pre Action Interceptors is instructions for the agent only.

Does Pre Action Interceptors access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Pre Action Interceptors safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Pre Action Interceptors use?

Pre Action Interceptors is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Pre Action Interceptors use?

About 580 tokens (SKILL.md is roughly 2.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Pre Action Interceptors?

Skills that share tags, products or a category with Pre Action Interceptors: Messages Ops (affaan-m/ECC, 277k stars), Actions (JetBrains/intellij-community, 21k stars), Laravel Actions (coollabsio/coolify, 63k stars) and Channel Message Flows (openclaw/openclaw, 392k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pre Action Interceptors?

Bitterbot-AI (a GitHub organization) maintains it in Bitterbot-AI/bitterbot-desktop, which has 2,471 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 11, 2026.

Source: Bitterbot-AI/bitterbot-desktop on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.