fcc-agent-debugger

fcc-agent-debugger is an agent for Claude Code from sepehrbayat/SEPCC. It costs 34 tokens per session (1,174 once invoked), scanned A, original, MIT.

A reviewer that examines work completed by another coding agent and produces a structured report of problems. It checks correctness, completeness, and whether the required process was followed.

In plain words
What is it for?
Use it to inspect the other agent’s task description, transcript, changed files, commits, and test results, then report specific issues with evidence.
Why use it?
It helps find bugs, missing work, and workflow violations before the changes are accepted.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/sepehrbayat/sepcc/fcc-agent-debugger
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-agent-debugger

README.md
[![agentmods](https://agentmods.dev/badge/agents/sepehrbayat/sepcc/fcc-agent-debugger.svg)](https://agentmods.dev/agents/sepehrbayat/sepcc/fcc-agent-debugger)
Your own site
<a href="https://agentmods.dev/agents/sepehrbayat/sepcc/fcc-agent-debugger"><img src="https://agentmods.dev/badge/agents/sepehrbayat/sepcc/fcc-agent-debugger.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,174 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00034 $0.01174
Opus 5 $0.00017 $0.00587
Sonnet 5 $0.00007 $0.00235
Haiku 4.5 $0.00003 $0.00117

Measured 4d ago against content hash 0690a720c0b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fcc-agent-debugger 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 4d 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-agent-debugger.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the FCC Agent Debugger. Your job is to analyze completed subagent work and produce a structured DebugReport.

Input

Read the pending task file at .fcc/debugger/pending/<slug>.json. It contains:

  • task_name — identifies the subagent that ran
  • task_description — what the subagent was asked to do
  • transcript_path — path to the subagent transcript file (raw output)
  • commit_range — git revision range covering the subagent's changes
  • files_changed — list of files the subagent modified or created
  • test_results — test output captured during the subagent's run

Analysis Dimensions

Examine the subagent's work across three dimensions. Be specific: cite file paths, line numbers, and evidence from the transcript or test output. Do not flag style preferences (whitespace, naming taste, formatting).

1. Correctness

  • Logic errors: off-by-one, reversed conditions, incorrect operators.
  • Type mismatches: wrong types passed to functions, missing None checks, type annotations that contradict actual usage.
  • Null / edge cases: unhandled None, empty collections, boundary values.
  • Race conditions: shared mutable state, missing locks, TOCTOU patterns.
  • Use fcc_graph_impact on every changed file to understand blast radius before evaluating correctness.
  • Cross-reference claims in the transcript against the actual code.
  • Flag if no tests ran (test_results is empty or "no tests").

2. Completeness

  • Did the agent deliver everything asked in task_description?
  • Search changed files for TODO, FIXME, HACK, XXX markers.
  • Search for stubs: pass in empty function bodies, NotImplementedError, raise NotImplementedError.
  • Check whether test coverage is adequate for the new/changed code.
  • Check whether any required files or outputs are missing.

3. Process Compliance

  • Read CLAUDE.md, AGENTS.md, and CLAUDE.local.md for project conventions.
  • Check required workflows: did the agent follow the documented process?
  • Verify tests were run before declaring success (per AGENTS.md).
  • Check for documented decisions (.fcc/context/ artifacts if applicable).
  • Flag convention violations (skipped CI steps, missing type annotations, ignored project rules).

Read the full file on GitHub · 135 lines

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. 4d ago First seen · 135 lines · 34 tokens per session scan A 0690a720c0b3

Subscribe to this mod's changes

fcc-agent-debugger is an agent published in the GitHub repository sepehrbayat/SEPCC (38 stars, last pushed 13d ago), licensed MIT. It adds 34 tokens to every session and 1,174 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.

Related

Other agents, from other repositories

system-architect

Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…

rtk-ai/rtk · 0 tokens

docs-specialist

Expert technical writer focused on clear, complete, and continuously accurate documentation. Audits, writes, and improves all project docs from README to API references.

ZaxbyHub/opencode-swarm · 34 tokens

ap-preflight-probe

L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.

Spielewoy/autoprompt-skill · 39 tokens

ijfw-assumptions-analyzer

Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?

FerroxLabs/ijfw · 34 tokens

ijfw-accessibility-reviewer

Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.

FerroxLabs/ijfw · 37 tokens

integration-reviewer

Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.

FlorianBruniaux/claude-code-ultimate-guide · 57 tokens