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.
npx agentmods add commands/viacheslav-tronko/claude-code-harness/bug-fullgit clone --depth 1 https://github.com/viacheslav-tronko/claude-code-harnessWrote 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.
[](https://agentmods.dev/commands/viacheslav-tronko/claude-code-harness/bug-full)<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>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.
| Model | Per session | Once 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 |
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.
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:
/bug-why $ARGUMENTS --full→ RCA (read-only). Skill:root-cause-analysis./verify <RCA>→ VERIFY-RCA; promotes RCA tostate: verifiedif PASS (read-only). Skill:task-verification./trace --virtual <RCA>→ TRACE-VIRTUAL; white-box falsification of fix plan before implementation (read-only). Skill:white-box-trace.- ASK USER (Two-Stage Confirm) — code modification is irreversible (§4.3 promoted to execute-time gate).
/bug-fix <RCA>→ applies §7.1 PRIMARY fix. Skill:surgical-implementation(MODE=FIX)./trace --real <FIX>→ TRACE-REAL; white-box CFG/MPC verification of applied fix; on FAIL providesfix_proposal(read-only). Skill:white-box-trace./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)
$ARGUMENTSempty → 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-fixseparately. - 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.
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.
- 5d ago First seen · 128 lines · 0 tokens per session scan A 9a5d927eec55
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.
Other commands, from other repositories
toh-help
Display all Toh Framework commands and quick usage guide.
new
Plan mode. Generates a plan for a feature based on a description.
feature
Create a feature specification using spec-driven development.
deep-audit.skeleton
Aciklama: Bu bolum Bootstrap tarafindan manifest verileriyle doldurulur. Gerekli manifest alanlari: project.description, stack.primary, project.structure, project.subprojects, stack.orm, stack.authmethod Ornek cikti.
fix-issue
!gh issue view $ARGUMENTS 2>/dev/null || echo "Could not fetch issue $ARGUMENTS".
rev
Invoke Code Reviewer for code quality, security, requirements validation, and best practices review.