Instructions file
Instructions for nirecom/agents, covering global claude code instructions, workflow and notes.
3 2d ago A 945 tokens
original MIT
Agent
Drafts and revises implementation plans. Used by the make-detail-plan skill in a planner/reviewer discussion loop.
3 2d ago A 27 tokens
original MIT
Agent
Critically reviews implementation plans produced by the detail-planner agent. Thorough — surfaces minor issues as well as major ones. Used by the make-detail-plan skill.
3 2d ago A 36 tokens
original MIT
Agent
3-pass GitHub issue dedupe survey. Classifies verdict (none/reopen/sub-of/make-parent/sibling) and writes a JSON artifact. Read-only — no issue creation, no comments.
3 2d ago B 46 tokens
original MIT
Agent
Proposes 2-3 mutually-exclusive high-level approaches for a task. Used by the make-outline-plan skill. Inspired by Aider's architect/editor split and GitHub Spec Kit's /specify stage.
3 2d ago A 46 tokens
original MIT
Agent
Reviews high-level approaches proposed by outline-planner. Checks direction and coverage only — never implementation details. Used by the make-outline-plan skill.
3 2d ago A 32 tokens
original MIT
Agent
CC fallback security-plan reviewer for review-plan-security; invoked when codex CLI is unusable.
3 2d ago A 24 tokens
original MIT
Agent
LLM judge for /refactor-prompts. Classifies hot regions from the lexical scan and emits an edit plan JSON.
3 2d ago A 32 tokens
original MIT
Agent
Scan code for security anti-patterns across three axes. Read-only, no web access. Used by review-code-security.
3 2d ago A 28 tokens
original MIT
Agent
Verifies whether a speculative skip (outline or detail) is safe based on session intent and outline artifacts.
3 2d ago A 25 tokens
original MIT
Agent
EM Supervisor — audit mode review agent. Invoked by Stop-hook block at stage boundaries (CONFIRMINTENT/OUTLINE/DETAIL) or when cumulative severity reaches the audit threshold. Reviews cross-stage coherence and writes a verdict (CONTINUE/WARN/BLOCK) to the supervisor state file.
3 2d ago A 64 tokens
original MIT
supervisor
12Agent
EM Supervisor — alert mode review agent. Invoked by Stop-hook block when C1 sentinel hang, C2 scheduled-review, or C3 off-proposal is detected. Reviews the active session against JD checklist and writes findings to the supervisor state file.
3 2d ago A 53 tokens
original MIT
survey-code
13Agent
Investigate the codebase to understand existing patterns, constraints, and relevant files. Writes a session-scoped survey-code.md artifact.
3 2d ago A 29 tokens
original MIT
Agent
Investigate git history and GitHub issue/PR timeline since the relevant issue opened, to surface changes that may invalidate the issue's premises.
3 2d ago A 31 tokens
original MIT
Agent
CC fallback test-coverage reviewer for review-tests; invoked when codex CLI is unusable.
3 2d ago A 23 tokens
original MIT
Agent
Research an external topic via WebSearch and WebFetch. Read-only. Used by deep-research.
3 2d ago A 25 tokens
original MIT
Skill Claude CodeCodex
Complete a task and run post-processing.
3 2d ago A 10 tokens
original MIT
start-task
18Skill Claude CodeCodex
Start a task (phase implementation, incident response, or improvement).
3 2d ago A 16 tokens
original MIT
Skill Claude CodeCodex
Map application-layer AWS resources (ECS, Lambda, ALB, API Gateway) and write a topology to AWSSTATEDIR.
3 2d ago A 32 tokens
original MIT
Skill Claude CodeCodex
Query current AWS billing data and identify top cost drivers using Cost Explorer.
3 2d ago A 19 tokens
original MIT
Skill Claude CodeCodex
Enumerate AWS compute, storage, network, and IAM resources and write a structured inventory to AWSSTATEDIR.
3 2d ago A 28 tokens
original MIT
Skill Claude CodeCodex
Evaluate IAM posture, public exposure, and security service status of the current AWS account.
3 2d ago A 22 tokens
original MIT
aws-scan
23Skill Claude CodeCodex
Orchestrate a full AWS infrastructure scan across resources, security, cost, and applications.
3 2d ago A 22 tokens
original MIT
Skill Claude CodeCodex
Conduct a decision-tree interview with the user to lock in requirements, motivation, scope, and non-goals before planning.
3 2d ago A 29 tokens
original MIT