SEPCC: Agent for Claude Code

.claude/agents/fcc-context-auditor.md

fcc-context-auditor is an agent for Claude Code from sepehrbayat/SEPCC. It costs 35 tokens per session (192 once invoked), scanned A, original, MIT.

An agent that audits whether a coding session's context was preserved across handoffs, resumes, compaction, or hook activity. It checks project notes, stored facts, decisions, memory, and the context knowledge graph.

In plain words
What is it for?
Use it to inspect context continuity, identify stale records or duplicate ownership, and suggest repairs to handoff information.
Why use it?
It helps detect missing or outdated information that could cause an agent to misunderstand the current state of work.

Agent for Claude Code

Written for Claude Code: SessionStart hook event.

This is sepehrbayat/SEPCC's own configuration. It tells Claude Code how to work on SEPCC itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything SEPCC configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sepehrbayat/SEPCC. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sepehrbayat/SEPCC/main/.claude/agents/fcc-context-auditor.md
Clone the repo
git clone --depth 1 https://github.com/sepehrbayat/SEPCC

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for fcc-context-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/sepehrbayat/sepcc/fcc-context-auditor.svg)](https://agentmods.dev/agents/sepehrbayat/sepcc/fcc-context-auditor)
Your own site
<a href="https://agentmods.dev/agents/sepehrbayat/sepcc/fcc-context-auditor"><img src="https://agentmods.dev/badge/agents/sepehrbayat/sepcc/fcc-context-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 192 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.00192
Opus 5 $0.00017 $0.00096
Sonnet 5 $0.00007 $0.00038
Haiku 4.5 $0.00003 $0.00019

Measured 8d ago against content hash 3656ab74ebdd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

fcc-context-auditor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/fcc-context-auditor.md · 16 lines

What it actually says

You audit FCC context continuity.

  • Start from SessionStart context and .fcc/context/handoff.md.
  • Check CLAUDE.local.md, .fcc/context/facts.md, and .fcc/context/decisions.md for durable facts.
  • Use MemSearch for persistent memory and Token Savior for code retrieval when available.
  • Do not replay raw transcripts; reference SQLite sidecar handles for raw logs.
  • Use fcc_graph_stats to check if the knowledge graph is stale vs HEAD — flag stale graphs.
  • Use fcc_graph_god_nodes to verify the structural anchors in handoff match reality.
  • Report gaps, stale context, duplicate owners, and next repair actions concisely.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 16 lines · 35 tokens per session scan A 3656ab74ebdd

Subscribe to this mod's changes

fcc-context-auditor is an agent published in the GitHub repository sepehrbayat/SEPCC (38 stars, last pushed 16d ago), licensed MIT. It adds 35 tokens to every session and 192 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.