agent-core
01Skill Claude CodeCodex
Parent skill for core agent cognition, safety, memory, taskflow, approvals, system readiness, and self-improvement workflows.
10 22d ago A 28 tokens
original MIT
10Stars on the repository
60Mods indexed here, across every type
22d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Skill Claude CodeCodex
Apply user, stranger, group, channel, and action access tiers using native channel policy, allowlists, approvals, and cognitive review.
10 22d ago A 31 tokens
original MIT
Skill Claude CodeCodex
Assess the assistant's readiness, capability fit, safety risks, tool coverage, and verification plan before or during complex work. Use when work is high-impact, ambiguous, risky, long-running, or failure-prone.
10 22d ago A 48 tokens
original MIT
Skill Claude CodeCodex
Review recent agent behavior, uncertainty, mistakes, interaction quality, and lessons so the assistant can improve future work. Use after complex tasks, failures, user corrections, or long sessions.
10 22d ago A 41 tokens
original MIT
Skill Claude CodeCodex
Treat unmentioned group-room chatter as quiet context unless policy, mention, direct request, or model-led cognition decides a response is appropriate. Use for Slack channels, Discord servers, Telegram groups, Matrix rooms, and similar shared spaces.
10 22d ago A 50 tokens
original MIT
Skill Claude CodeCodex
Require explicit human approval before purchases, messages, installs, file writes, remote API mutations, app control, or other irreversible actions.
10 22d ago A 33 tokens
original MIT
Skill Claude CodeCodex
Inspect run history, approvals, outbox, interpreter manifests, screenshots, and memory events to reconstruct what the agent actually did.
10 22d ago A 30 tokens
original MIT
Skill Claude CodeCodex
Run bounded autonomous cycles over queued events, due wakeups, ready tasks, and optional initiative while preserving approvals and stop conditions. Use when configuring, testing, or operating Stram as a continuing assistant.
10 22d ago A 46 tokens
original MIT
Skill Claude CodeCodex
Prevent bot-to-bot reply loops by detecting bot-authored inbound messages, pair suppression, channel policy, and ambient context rules. Use when handling channels that may receive messages from other assistants or automation.
10 22d ago A 45 tokens
original MIT
Skill Claude CodeCodex
Audit Stram's effective tools, skills, plugins, channels, providers, local services, and missing capability gaps. Use before large integrations, after adding tools, or when the user asks what the agent can currently do.
10 22d ago A 49 tokens
original MIT
Skill Claude CodeCodex
Design and inspect Stram tools, skills, plugins, adapters, and setup surfaces without brittle intent routing or third-party package assumptions.
10 22d ago A 31 tokens
original MIT
Skill Claude CodeCodex
Decide what matters most next across active goals, commitments, wakeups, environment constraints, risks, and opportunities. Use when choosing next work, triaging competing tasks, or recovering focus.
10 22d ago A 44 tokens
original MIT
Skill Claude CodeCodex
Curate assistant memory by retaining useful knowledge, summarizing noisy history, archiving stale records, and forgetting unsupported details. Use when memory feels noisy, outdated, duplicated, or too large.
10 22d ago A 42 tokens
original MIT
Skill Claude CodeCodex
Update assistant persona, communication style, user preferences, boundaries, and stable facts from evidence. Use when the user corrects behavior, states preferences, or asks the assistant to become more personally useful.
10 22d ago A 43 tokens
original MIT
Skill Claude CodeCodex
Screen untrusted text, webpages, documents, and channel messages for prompt-injection, exfiltration, tool-abuse, and instruction-conflict risks.
10 22d ago A 37 tokens
original MIT
Skill Claude CodeCodex
Prevent leakage of API keys, tokens, credentials, private keys, personal data, and sensitive clipboard/env/log content across tools and channels.
10 22d ago A 32 tokens
original MIT
Skill Claude CodeCodex
End a work session by summarizing completed work, blockers, tests, pending commitments, memory lessons, and optional git status. Use when the user asks to wrap up, checkpoint, commit, or preserve learnings.
10 22d ago A 47 tokens
original MIT
Skill Claude CodeCodex
Check local system readiness, disks, environment, integrations, voice/browser/channel providers, and dependency health before or during agent workflows.
10 22d ago A 29 tokens
original MIT
Skill Claude CodeCodex
Track tasks, commitments, blockers, statuses, and next actions across ongoing user work. Use when the user asks what is pending, what changed, what is blocked, what should be updated, or how to keep a task moving.
10 22d ago A 50 tokens
original MIT
taskflow
20Skill Claude CodeCodex
Coordinate durable multi-step work with goals, tasks, waits, wakeups, autonomous cycles, and child/delegated tasks.
10 22d ago A 28 tokens
original MIT
Skill Claude CodeCodex
Create, review, evaluate, and cancel future reminders, wakeups, and triggers for the assistant. Use when the user wants follow-ups, timed checks, reminders, monitors, or future task continuation.
10 22d ago A 45 tokens
original MIT
browser-web
22Skill Claude CodeCodex
Parent skill for web browsing, browser automation, web evidence gathering, web forms, browser testing, extraction, and web artifact workflows.
10 22d ago A 29 tokens
original MIT
Skill Claude CodeCodex
Use browser, Playwright, and computer-use style tools through observed state and approval-gated actions.
10 22d ago A 25 tokens
original MIT
Skill Claude CodeCodex
Use search, static fetch, and live browser tools for current web evidence with observation-first browser discipline, date verification, anti-churn rules, and approval-gated interactions.
10 22d ago A 40 tokens
original MIT