Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add oeftimie/vv-claude-harness/plugin install vv-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/skills/oeftimie/vv-claude-harness/harness-continue)<a href="https://agentmods.dev/skills/oeftimie/vv-claude-harness/harness-continue"><img src="https://agentmods.dev/badge/skills/oeftimie/vv-claude-harness/harness-continue/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/oeftimie/vv-claude-harness/harness-continue"><img src="https://agentmods.dev/badge/skills/oeftimie/vv-claude-harness/harness-continue.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00061 | $0.07977 |
| Opus 5 | $0.00030 | $0.03988 |
| Sonnet 5 | $0.00012 | $0.01595 |
| Haiku 4.5 | $0.00006 | $0.00798 |
Grade A, and why
harness-continue 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 10d 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 — 519 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness Continue
Step 1: Orient Yourself
The vv-harness plugin's SessionStart hook auto-injects orientation at session start: feature summary, next claimable feature, last handoff, Active Context, a git identity warning on mismatch, and any SESSION_INCOMPLETE gaps from the previous session. Use that injected "## Harness orientation" block instead of re-reading the harness files. Resolve any SESSION_INCOMPLETE gaps it surfaces before starting new work.
This skill covers what the hook does not: mode choice, the smoke test, and workflow planning.
Check for untracked files and inherited task quality:
git status -s # surface unknown untracked files
If you see untracked files you didn't create (e.g., notes.md, scratch files), surface them to the user immediately: "I see [file] untracked — should I delete it, gitignore it, or leave it?" This takes 5 seconds and prevents orphaned file accumulation.
If inheriting tasks from a previous session, verify they have required metadata fields (feature_id at minimum) via TaskList. Tasks without feature_id can't be correlated by hooks or retrospectives. Update them with TaskUpdate now if they're missing it.
Step 2: Verify Git Identity
The SessionStart hook already compared git config user.email against
.harness/harness.json and warned on mismatch (non-blocking). If the orientation
block shows an identity warning, fix it before proceeding. Also verify the SSH
identity, which the hook does not check:
ssh -T [email protected] 2>&1 || true
Do not skip this.
Step 2.5: Smoke Test
Run the project's build/test smoke test:
./.harness/init.sh smoke_test
This is a gate, not a diagnostic. Its purpose is to confirm the environment is in a known-good state BEFORE any changes. If it fails, you know the problem is pre-existing, not something you introduced. Run it within the first 5 actions of every session. No exceptions. The 15-second cost prevents 15-minute debugging sessions later. (OVI-106: init.sh's own default target is full_test, not smoke_test -- pass the argument explicitly, or this step silently runs the full suite instead of the fast gate this section describes.)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 519 lines · 61 tokens per session scan A edb4fa100053
harness-continue is a skill published in the GitHub repository oeftimie/vv-claude-harness (19 stars, last pushed 18d ago), licensed MIT. It adds 61 tokens to every session and 7,977 once invoked, about $0.0003 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.
Other skills, from other repositories
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.
python
Python development with ruff, mypy, pytest - TDD and type safety.
nw-fp-clojure
Clojure language-specific patterns, data-first modeling, REPL-driven development, and spec.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
mobiai-mobile-tdd
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.