Skill Claude CodeCodex
Recall project state without prompt replay. Use when resuming work, checking prior decisions, or needing context from earlier sessions.
38 10d ago A 28 tokens
original MIT
Skill Claude CodeCodex
Update the compact FCC handoff at the end of meaningful work or before compaction.
38 10d ago A 22 tokens
original MIT
route-task
03Skill Claude CodeCodex
Choose the FCC model tier for a task using .fcc/router.yml.
38 10d ago A 17 tokens
original MIT
Agent Claude Code
Analyzes completed subagent work for correctness, completeness, and process compliance. Produces a structured DebugReport consumed by fcc-agent-fixer.
38 10d ago A 34 tokens
original MIT
Agent Claude Code
Fixes issues found by fcc-agent-debugger. Reads a DebugReport, fixes each finding in priority order, verifies with tests, commits results.
38 10d ago A 35 tokens
original MIT
Agent Claude Code
Use proactively for non-trivial code changes, regressions, migrations, or before final verification. Focus on correctness and tests.
38 10d ago A 30 tokens
original MIT
Agent Claude Code
Use proactively when context, handoff, memory, session resume, compaction, or hook behavior may affect the task. Avoid for trivial edits.
38 10d ago A 35 tokens
original MIT
Agent Claude Code
Use proactively when UX, workflow, route policy, session resume behavior, plugin policy, or agent autonomy decisions are part of the task.
38 10d ago A 34 tokens
original MIT
Agent Claude Code
Use proactively for current documentation, ecosystem, plugin, hook, MCP, or external best-practice research. Prefer primary sources.
38 10d ago A 30 tokens
original MIT
PreCompact
10Hook Claude Code
Runs before the context is compacted, executing precompact.py via uv. From sepehrbayat/SEPCC.
38 10d ago A
tokens not measured
original MIT
SessionStart
11Hook Claude Code
Runs when a session starts, executing session_start.py via uv. From sepehrbayat/SEPCC.
38 10d ago A
tokens not measured
original MIT
Stop
12Hook Claude Code
Runs when the agent finishes a response, executing stop.py via uv. From sepehrbayat/SEPCC.
38 10d ago A
tokens not measured
original MIT
SubagentStop
13Hook Claude Code
Runs when a subagent finishes, executing subagent_stop.py via uv. From sepehrbayat/SEPCC.
38 10d ago A
tokens not measured
original MIT
Hook Claude Code
Runs when you submit a prompt, before the agent sees it, executing user_prompt_submit.py via uv. From sepehrbayat/SEPCC.
38 10d ago A
tokens not measured
original MIT
SEPCC
15Settings file Claude Code
Agent settings declaring 5 hook events (PreCompact, SessionStart, Stop, SubagentStop).
38 10d ago A
tokens not measured
original MIT
fcc-graph
16MCP server Claude CodeCodexCursor +2
MCP server "fcc-graph" as configured in sepehrbayat/SEPCC. Runs locally from the python Python package. Needs 1 environment variable to run.
38 10d ago A
tokens not measured
original MIT
token-savior
17MCP server Claude CodeCodexCursor +2
Optimized MCP server for AI coding agents. Structural codebase navigation + persistent memory engine — 97.9% accuracy at −80% tokens on tsbench. Runs locally from the token-savior-recall Python package. Needs 3 environment variables to run.
38 10d ago A
tokens not measured
original MIT
Instructions file CodexOpenCode
Instructions for sepehrbayat/SEPCC, covering agentic directive, coding environment, identity & context, architecture principles and cognitive workflow.
38 10d ago C 971 tokens
copy · 78% MIT
Instructions file
Instructions for sepehrbayat/SEPCC: IMPORTANT: Ensure you’ve thoroughly reviewed the AGENTS.md file before beginning any work.
38 10d ago A 23 tokens
copy · 100% MIT
handoff
20Command Claude Code
Regenerate .fcc/context/handoff.md with.
38 10d ago A 0 tokens
original MIT
recall
21Command Claude Code
Use this order.
38 10d ago A 0 tokens
original MIT
Command Claude Code
Check that.
38 10d ago B 0 tokens
original MIT
Skill Claude CodeCodex
Choose when to use Claude Code built-in commands before adding FCC-specific workflow.
38 10d ago A 20 tokens
original MIT