bob-agent-rules
Use when the user asks which rules IBM Bob injects — subagents ("do the work yourself"), which model or tier is used, why answers stay inline, how AGENTS.md…
Skill by elpfries
Chalk Labs
Need help deploying bob-agent-rules?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/elpfries-bob-agent-rules
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 1, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/bob-agent-rules/opt/bobide/resources/app/opt/ibm-bob/resources/app/usr/share/bobide/resources/app/usr/share/ibm-bob/resources/app- Your home directory (~)
What's inside
- Skill name
bob-agent-rules- Description
- Use when the user asks which rules IBM Bob injects — subagents ("do the work yourself"), which model or tier is used, why answers stay inline, how AGENTS.md and .bob/rules rank — or wants to see the actual system prompt Bob used.
- License
- MIT
- Instructions
- 14 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (5)
- SKILL.md
- command-migration.md · reference/
- injected-rules.md · reference/
- _bobcheck.py · scripts/
- dump_system_prompt.py · scripts/
SKILL.md (first lines)
# Rules Bob injects 1. `python3 "<skill-dir>/scripts/dump_system_prompt.py" --list`, then `--section NAME`, `--guidance Subagents` (or `create_html_artifact`), `--grep REGEX`, `--task PREFIX`, `--all`. This is the prompt Bob really used, stored with the task. 2. Skills appearing in `.bob/skills/` on their own, or coming back after deletion: read `reference/command-migration.md` — Bob turns `commands/*.md` files into skills at every start, and `/init` is not involved. 3. For what the prompt does not show — subagent presets and their models, tier → alias table, rule precedence, custom agents — read `reference/injected-rules.md`. 4. State that rules are instructions, not enforcement, and that `explore` subagents never see project rules. To change any of it, use the `bob-override-rules` skill.
From elpfries/bob-sideshow, MIT.
More from elpfries/bob-sideshow
- 0.570score
pre-clear
elpfries
Auditer la conversation en cours avant un /clear, en supposant qu'elle s'arrête juste après — passe 0 sur ce qui tourne encore, passe 1 mécanique via un…
SkillAFreshness: AClaude Code +9 - 0.570score
bob-telemetry
elpfries
Use when the user asks what IBM Bob consumed or did — Bobcoins, tokens, cost per model class, per task or subagent, tools used, commands flagged as dangerous…
SkillAFreshness: AClaude Code +9 - 0.570score
quota-check
elpfries
Relever le quota d'abonnement Kimi Code (fenêtre 5 h, mensuel, Extra Usage) sans le TUI, via le serveur local de l'app Desktop ou de `kimi web`.
SkillAFreshness: AClaude Code +9 - 0.570score
task-telemetry
elpfries
Mesurer et persister la télémétrie réelle d'une tâche Backlog.md (appels, tokens, coût USD/EUR quand il existe, temps effectif vs pauses) depuis les…
SkillAFreshness: AClaude Code +9 - 0.570score
bob-override-rules
elpfries
Use when the user wants IBM Bob to follow their own rules instead of the built-in ones — always spawn a subagent when asked, premium model for subagents…
SkillAFreshness: AClaude Code +9 - 0.565score
analyze-task
elpfries
Analyser la conception d'une tâche Backlog.md avant que quiconque l'implémente — charger tout son contexte backlog, cartographier les points d'extension du…
SkillAFreshness: AClaude Code +9 - 0.565score
bob-security-model
elpfries
Use when the user asks why IBM Bob asks for approval, how approved or denied command patterns match (prefix, wildcard, case), what "Security warning" or…
SkillAFreshness: AClaude Code +9 - 0.565score
bob-version
elpfries
Use when the user asks which IBM Bob version, build, extension, Bob Shell, database schema or server-pushed models are in use.
SkillAFreshness: AClaude Code +9 - 0.565score
next-task
elpfries
Choisir la prochaine tâche Backlog.md à traiter — reprend la tâche In Progress s'il en existe une, sinon filtre les tâches To Do par dépendances résolues et…
SkillAFreshness: AClaude Code +9 - 0.555score
run-milestone
elpfries
Mener une milestone Backlog.md — ou une chaîne de plusieurs, l'une après l'autre — à son terme par une chaîne de sous-agents — résoudre l'ordre de traitement…
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 19, 2026 (21 days ago)
- Last release
- Oct 19, 2026 (21 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/elpfries/bob-sideshow
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from elpfries
- 0.570score
pre-clear
elpfries
Auditer la conversation en cours avant un /clear, en supposant qu'elle s'arrête juste après — passe 0 sur ce qui tourne encore, passe 1 mécanique via un…
SkillAFreshness: AClaude Code +9 - 0.570score
bob-telemetry
elpfries
Use when the user asks what IBM Bob consumed or did — Bobcoins, tokens, cost per model class, per task or subagent, tools used, commands flagged as dangerous…
SkillAFreshness: AClaude Code +9 - 0.570score
quota-check
elpfries
Relever le quota d'abonnement Kimi Code (fenêtre 5 h, mensuel, Extra Usage) sans le TUI, via le serveur local de l'app Desktop ou de `kimi web`.
SkillAFreshness: AClaude Code +9 - 0.570score
task-telemetry
elpfries
Mesurer et persister la télémétrie réelle d'une tâche Backlog.md (appels, tokens, coût USD/EUR quand il existe, temps effectif vs pauses) depuis les…
SkillAFreshness: AClaude Code +9 - 0.570score
bob-override-rules
elpfries
Use when the user wants IBM Bob to follow their own rules instead of the built-in ones — always spawn a subagent when asked, premium model for subagents…
SkillAFreshness: AClaude Code +9 - 0.565score
analyze-task
elpfries
Analyser la conception d'une tâche Backlog.md avant que quiconque l'implémente — charger tout son contexte backlog, cartographier les points d'extension du…
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get bob-agent-rules running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
bob-agent-rules skill. Agent Mart. https://agentmart.dev/skills/elpfries-bob-agent-rules (last updated 2026-10-24)