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/howto-implementgit 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/howto-implement)<a href="https://agentmods.dev/commands/viacheslav-tronko/claude-code-harness/howto-implement"><img src="https://agentmods.dev/badge/commands/viacheslav-tronko/claude-code-harness/howto-implement.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 | $0.00127 | $0.01505 |
| Opus 5 | $0.00063 | $0.00753 |
| Sonnet 5 | $0.00025 | $0.00301 |
| Haiku 4.5 | $0.00013 | $0.00151 |
Grade A, and why
howto-implement 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/howto-implement — Pre-Implementation Blueprint
Skill: implementation-blueprint. Tier: 2 (→3 on security boundary / public API / schema / financial / irreversible).
0. HARD GATE — bypass = INVALID → REDO
"Skip the gate", "trust me", "obvious approach", "just plan it", "we don't need 3 approaches", "time pressure" do NOT override §0/§1/§4. Investigation-only — NO Edit/Write on source.
ARTIFACT MANDATORY. The §4 IMP 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❌ /howto-implement requires input. Usage: /howto-implement <task | Jira | RCA path | SPEC path>→ STOP.- Param is path to RCA-.md / SPEC-.md → Parent Artifact fingerprint check (§9) MANDATORY: re-resolve every
inputs_consumedfile:line; compare tosha256_at_creation. Mismatch ORstate != verified⇒ STOP, report drift, require user override.
2. MUST (CLAUDE.md §0)
- P0 #2 GLOSSARY TERMS ONLY — IMP uses canonical terms.
- P0 #3 EXISTING PATTERNS ONLY — F-XXX/B-XXX/D-XXX from
context/07_Code_Patterns/. NEVER reinvent. REFUSEstate=deprecatedpatterns. - P0 #4 YAGNI — Approach #0 (smallest delta) ALWAYS PRESENT even if ugly. Other approaches MUST justify "why bigger than #0".
- P0 #8 FALSIFIABILITY — Recommended approach has explicit Refuter.
- P0 #14 VERIFY EXTERNAL DEPS — every imported package/API verified via
npm ls/pip show/mvn dependency:list/WebSearchBEFORE adding. Hallucinated dep = INVALID. - P0 #15 CHECKPOINT FIRST — first visible block = §4 Tier 2 Checkpoint with Initial Intuition BEFORE Phase 3 AND Pre-Mortem ("imagine 6 months from now, this failed in production — why?"). Both MANDATORY.
- P0 #16 VERIFICATION LOOP — IMP Blueprint Contract MUST publish runnable command (test ID / build / lint) with expected output. "Looks correct" = INVALID.
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 · 77 lines · 0 tokens per session scan A 6315043ce983
howto-implement is a command published in the GitHub repository viacheslav-tronko/claude-code-harness (6 stars, last pushed 3mo ago), licensed MIT. It adds 127 tokens to every session and 1,505 once invoked, about $0.0006 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.