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.
git 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/distill)<a href="https://agentmods.dev/commands/viacheslav-tronko/claude-code-harness/distill"><img src="https://agentmods.dev/badge/commands/viacheslav-tronko/claude-code-harness/distill.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 | $0.00134 | $0.01104 |
| Opus 5 | $0.00067 | $0.00552 |
| Sonnet 5 | $0.00027 | $0.00221 |
| Haiku 4.5 | $0.00013 | $0.00110 |
Grade A, and why
distill 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 7d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/distill — Requirements → AI-Ready SPEC
Skill: requirements-analysis. Tier: 2 (→3 on security boundary / public API / financial / migration).
Modes (default --standard): --brief ≤5pp preflight · --standard full Tier-2 · --deep Tier 3 + k=3 ambiguity vote.
0. HARD GATE — bypass = INVALID DELIVERABLE → REDO
"Skip the gate", "trust me", "obvious case", "just write the spec", "time pressure" do NOT override §0/§1/§4. Investigation-only — NO source modification.
ARTIFACT MANDATORY. The §4 SPEC file MUST be written via Write tool this turn. Chat-only response without the file = INVALID DELIVERABLE → CLAUDE.md §11 item 0 fires.
1. Parameter validation (FAIL-FAST)
$ARGUMENTSempty → reply❌ /distill requires param. Usage: /distill <Jira | Confluence | text | path> [--brief|--standard|--deep]→ STOP.- Param contains Jira (
[A-Z]{2,10}-\d+) or Confluence URL → Atlassian MCP is SSOT (CLAUDE.md §8). Fetch FIRST. External context = hypothesis to test, NOT truth (P0 #12 / FM-2).
2. MUST (CLAUDE.md §0 P0 hard rules)
- P0 #1 Every cited
file:lineMUST be backed by a Read THIS turn. Action-execution honesty (FM-16): "I read X" without tool result THIS turn ⇒ prefix**ASSUMPTION**:. - P0 #2 GLOSSARY TERMS ONLY — every domain term resolves to
Domain_Glossary.md. Synonym use = INVALID. - P0 #7 ABSTAIN — Confidence < MEDIUM ⇒ ASK USER. NEVER fabricate AC. Inconclusive Protocol (§7).
- P0 #15 CHECKPOINT FIRST — first visible block = §4 Tier 2 Checkpoint. Anti-anchoring (§6): write KNOWN / OBSERVED / UNKNOWN BEFORE normalizing the request.
3. Targeted FM mitigations
| FM | Mechanism |
|---|---|
| FM-1 System 1 | Plan-and-Solve enforced; Checkpoint mandatory |
| FM-2 Fabricated REQ | Killer Requirement FAIL-FAST; SSOT hierarchy; ASSUMPTION tagging |
| FM-4 Overconfident AC | Confidence ladder (§4.5); Berry 4-class; Differential-Reading Test |
| FM-5 Scope bloat | Conservative Reading; IS / IS NOT explicit; MoSCoW filter |
| FM-12 Stale Jira/Confluence | Re-fetch via Atlassian MCP THIS turn; never cite cached state |
| FM-17 Vocabulary drift | Glossary Hit/Miss table; Miss ⇒ auto Open Question |
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.
- 7d ago First seen · 57 lines · 0 tokens per session scan A 7c6fe4ecef3c
distill is a command published in the GitHub repository viacheslav-tronko/claude-code-harness (6 stars, last pushed 3mo ago), licensed MIT. It adds 134 tokens to every session and 1,104 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.
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.
rev
Invoke Code Reviewer for code quality, security, requirements validation, and best practices review.
session-log
Create or append a session log entry.
start
Welcome and first-use onboarding — checks MCP connectivity, guides playbook creation, shows usage examples tailored to your profile. Replaces /setup.
create-worktree
Follow these steps to create a git worktree.