Hoja-Solutions

Hoja-Solutions/agent-stdlib

Plugin Claude Code

Plugin marketplace listing 1 plugin: agent-stdlib.

Hoja-Solutions/agent-stdlib

Plugin Claude Code

Agent-building practices from Anthropic's engineering blog, packaged as installable Claude Code skills, MCP servers, and safety hooks for tool-gating and prompt-injection screening. Covers the gaps no existing skill pack fills.

Hoja-Solutions/agent-stdlib

MCP server Claude CodeCodexCursor

MCP server "agent-stdlib-think" as configured in Hoja-Solutions/agent-stdlib. Runs locally from the ${CLAUDE_PLUGIN_ROOT}/mcp-servers/think/server.py Python package.

Hoja-Solutions/agent-stdlib

MCP server Claude CodeCodexCursor

MCP server "agent-stdlib-tool-gateway" as configured in Hoja-Solutions/agent-stdlib. Runs locally from the ${CLAUDE_PLUGIN_ROOT}/mcp-servers/tool-gateway/server.py Python package.

Hoja-Solutions/agent-stdlib

Instructions file CodexOpenCode

AGENTS.md instructions for Hoja-Solutions/agent-stdlib, covering using agent-stdlib in any harness, what ports cleanly, what needs re-wrapping, use the skills as plain content and mount the mcp servers.

Hoja-Solutions/agent-stdlib

Agent

Worker subagent for an orchestrated research run. Takes one objective and a notes-file path, searches broad-to-narrow, writes cited findings to the file, and returns a short summary. Dispatched by the /research command, not for direct use.

Hoja-Solutions/agent-stdlib

Command

Set up and explain the lock-file autonomy loop for running unsupervised agents on one shared repo.

Hoja-Solutions/agent-stdlib

Command

Run an orchestrator-worker research pass that decomposes a question into parts, dispatches parallel research-worker subagents, and synthesizes a cited answer.

Hoja-Solutions/agent-stdlib

Hook

Runs before the agent uses a tool for Bash tool calls, executing action_gate.py via python3. From Hoja-Solutions/agent-stdlib.

Hoja-Solutions/agent-stdlib

Hook

Runs after a tool call finishes for WebFetch tool calls, executing injection_screen.py via python3. From Hoja-Solutions/agent-stdlib.

Hoja-Solutions/agent-stdlib

Skill Claude CodeCodex

Give an agent access to many tools without flooding its context with every tool definition. Covers the three advanced-tool-use patterns: a search tool the agent calls to discover tools on demand, programmatic tool calling where the model writes code that invokes tools and filters results before they return, and…

Hoja-Solutions/agent-stdlib

Skill Claude CodeCodex

Ship a change to a running agent without degrading it, and keep a long-running agent reliable. Covers gating every system-prompt or model change behind a broad eval run, rolling out in stages and watching for report spikes, treating the agent's reasoning or thinking state as an invariant a cache must not drop, giving…

Hoja-Solutions/agent-stdlib

Skill Claude CodeCodex

Audit an agent for risky behavior before it ships, the way you would red-team it, but automated. An auditor agent runs many multi-turn scenarios against your target agent from seed instructions you write, and a judge model scores the transcripts for deception, sycophancy, oversight subversion, power-seeking, and…

Hoja-Solutions/agent-stdlib

Skill Claude CodeCodex

Build automated evaluations for an AI agent from scratch: collecting tasks from real failures, choosing code/model/human graders, picking pass@k vs pass^k, building an isolated harness, and keeping the suite honest over time. Use this whenever someone wants to measure, benchmark, or regression-test an agent, write an…

Hoja-Solutions/agent-stdlib

Skill Claude CodeCodex

Stop the machine from deciding your benchmark. Configure and validate the container and runtime resources for an agentic coding eval so infrastructure noise stays inside statistical bounds instead of swinging scores more than the models do. Use this whenever someone runs SWE-bench or any agentic coding benchmark in…

Hoja-Solutions/agent-stdlib

Skill Claude CodeCodex

Design the tool interface for a coding agent so the model stops misusing it. Covers the minimal two-tool scaffold (a bash tool plus a file editor), exact single-match string replacement, absolute-path rules, and error-proofing the tool descriptions so common model mistakes become impossible. Use this whenever someone…

Hoja-Solutions/agent-stdlib

Skill Claude CodeCodex

Screen an agent's input and output against a policy you write, so it refuses the content classes you disallow without over-refusing the ones you allow. Covers writing a constitution that lists allowed and disallowed content for your app, screening user input before the model and model output before delivery…

Hoja-Solutions/agent-stdlib

Skill Claude CodeCodex

Keep an agent from obeying instructions hidden in the content it reads. Covers placing fetched pages, emails, and API responses in toolresult blocks instead of the system prompt; wrapping that content as JSON with explicit source fields; labeling its provenance; screening tool output with a fast classifier before the…

Hoja-Solutions/agent-stdlib

Skill Claude CodeCodex

Structure a long-lived agent service so any part can crash and resume. Decompose it into brain (model plus harness), hands (ephemeral sandbox and tools), and session (a durable event log), each replaceable on its own, with wake/resume semantics and credentials kept out of the execution environment. Use this whenever…

Hoja-Solutions/agent-stdlib

Skill Claude CodeCodex

Run an orchestrator-worker system for breadth-first research: a lead agent plans, spawns three to five subagents with their own context windows, and synthesizes their findings. Covers when multi-agent actually beats a single agent and when it just burns tokens, how to delegate so subagents do not overlap…

Hoja-Solutions/agent-stdlib

Skill Claude CodeCodex

Coordinate several unsupervised agents working on one shared git repo without collisions. Covers the autonomy loop that lets each agent pick the next task and respawn without a human, file-based lock files that claim work, machine- readable test output so a test suite steers the agents instead of a person, and context…

Hoja-Solutions/agent-stdlib

Skill Claude CodeCodex

Keep an agent from gaming a checkable objective instead of doing the work. An agent told to make tests pass may delete the failing test, hard-code the expected output, or special-case the grader; the task looks done and its intent is defeated. Covers spotting reward-hacking in transcripts and evals, inoculation…

Hoja-Solutions/agent-stdlib

Skill Claude CodeCodex

Contain an agent that runs code or reads untrusted content, layer by layer. Covers OS-level filesystem and network isolation that also catches spawned subprocesses, an egress proxy that checks request provenance, treating tool outputs and fetched pages as prompt-injection vectors, and keeping credentials outside the…

Hoja-Solutions/agent-stdlib

Skill Claude CodeCodex

Decide where an agent should reason during a task and how to prompt for it. Covers three places a model can think and how to choose between them: extended thinking before the turn, interleaved thinking between tool calls, and the no-op "think" tool that logs reasoning mid-chain at a point you pick. Also covers when a…