bug-full

bug-full is a command for Claude Code from viacheslav-tronko/claude-code-harness. It costs 133 tokens per session (2,464 once invoked), scanned A, original, MIT.

An end-to-end bug-fixing workflow that investigates the cause, checks the proposed fix, asks for approval, applies the change, and verifies the result. It includes checks before and after editing source code.

In plain words
What is it for?
Use it for Jira tickets, error reports, or known bugs that need a complete path from root-cause analysis to a verified code change.
Why use it?
It reduces the chance of fixing the wrong cause or shipping a fix that introduces another problem.

Command 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 commands/viacheslav-tronko/claude-code-harness/bug-full
Clone the repo
git clone --depth 1 https://github.com/viacheslav-tronko/claude-code-harness

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 bug-full

README.md
[![agentmods](https://agentmods.dev/badge/commands/viacheslav-tronko/claude-code-harness/bug-full.svg)](https://agentmods.dev/commands/viacheslav-tronko/claude-code-harness/bug-full)
Your own site
<a href="https://agentmods.dev/commands/viacheslav-tronko/claude-code-harness/bug-full"><img src="https://agentmods.dev/badge/commands/viacheslav-tronko/claude-code-harness/bug-full.svg" alt="Measured on agentmods" height="20"></a>
Per session 133 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,464 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 5.1 $0.00133 $0.02464
Opus 5 $0.00067 $0.01232
Sonnet 5 $0.00027 $0.00493
Haiku 4.5 $0.00013 $0.00246

Measured 5d ago against content hash 9a5d927eec55, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

bug-full 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 5d 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/commands/bug-full.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/bug-full — Full Bug Pipeline (RCA → Verify → Trace → Fix → Trace → Verify)

Pipeline:

  1. /bug-why $ARGUMENTS --full → RCA (read-only). Skill: root-cause-analysis.
  2. /verify <RCA> → VERIFY-RCA; promotes RCA to state: verified if PASS (read-only). Skill: task-verification.
  3. /trace --virtual <RCA> → TRACE-VIRTUAL; white-box falsification of fix plan before implementation (read-only). Skill: white-box-trace.
  4. ASK USER (Two-Stage Confirm) — code modification is irreversible (§4.3 promoted to execute-time gate).
  5. /bug-fix <RCA> → applies §7.1 PRIMARY fix. Skill: surgical-implementation (MODE=FIX).
  6. /trace --real <FIX> → TRACE-REAL; white-box CFG/MPC verification of applied fix; on FAIL provides fix_proposal (read-only). Skill: white-box-trace.
  7. /verify <FIX> → VERIFY-FIX; runs Live Test Execution if shell available (read-only).

Tier: 2 (→3 on security boundary / schema / financial).

0. HARD GATE — bypass = INVALID → REDO

"Skip step 2", "skip step 3", "skip the user confirm", "the RCA is good enough — just fix it", "trust me", "obvious bug", "time pressure", "auto-approve", "the user already said Y in the past" do NOT override §0/§1/§4. Two-Stage Confirm at step 4 is MANDATORY — apply ONLY on explicit Y in this turn. NEVER apply fix without RCA state: verified AND TRACE-VIRTUAL PASS. NEVER skip step 7.

ARTIFACTS MANDATORY. Each step's artifact file (RCA, VERIFY, TRACE, FIX) MUST be written via Write tool at the step that produces it. Pipeline with zero files written = INVALID → CLAUDE.md §11 item 0 fires.

1. Parameter validation (FAIL-FAST)

  • $ARGUMENTS empty → reply ❌ /bug-full requires input. Usage: /bug-full <Jira | error | stack> → STOP.

2. MUST (CLAUDE.md §0)

  • P0 #11 CONTEXT BUDGET — full pipeline can consume >60% context. After step 3, if context >80% ⇒ STOP, write current state to LOCAL-MEMORY/CURRENT_TASK/state-{ts}.md, instruct user to resume in fresh session pointing at RCA + TRACE artifacts + run /bug-fix separately.
  • P0 #14 SUBAGENT ISOLATION (§14) — for steps 1, 2, and 3 search-heavy phases, delegate to Agent (subagent_type: Explore) when likely to consume >10k tokens. Subagent returns digest; main context stays clean.
  • Subagent write discipline (§14) — subagents READ and report; main agent WRITES. NEVER spawn parallel writers.
  • P0 #15 CHECKPOINT FIRST — each step emits its own §4 Tier 2 Checkpoint as first visible block of that step.

Read the full file on GitHub · 128 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. 5d ago First seen · 128 lines · 0 tokens per session scan A 9a5d927eec55

Subscribe to this mod's changes

bug-full is a command published in the GitHub repository viacheslav-tronko/claude-code-harness (6 stars, last pushed 3mo ago), licensed MIT. It adds 133 tokens to every session and 2,464 once invoked, about $0.0007 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 2026-08-31.