trial

A delivery check for coding agents that requires fresh evidence before making claims about completed code or file changes.

In plain words
What is it for?
For reviewing acceptance criteria, testing the claimed behavior, recording command results, and deciding whether a final response can truthfully say the work is complete.
Why use it?
It reduces unsupported claims by checking that each result, test, and completion statement is backed by a command run for the current task.

Skill for Claude CodeCodex

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 skills/da7-tech/trial/claude
Any agent
npx skills add Da7-Tech/trial --skill claude
Clone the repo
git clone --depth 1 https://github.com/Da7-Tech/trial

Made for: Claude Code, Codex.

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 709 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 $0.00045 $0.00709
Opus 5 $0.00023 $0.00354
Sonnet 5 $0.00009 $0.00142
Haiku 4.5 $0.00005 $0.00071

Measured yesterday against content hash a8047570f84e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

trial 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 yesterday.

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.

agents/claude/SKILL.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trial — Pre-Delivery Evidence Gate

Do not send "done." Prove it first.

Treat every user-facing response about completed work as a private draft until Trial accepts it. Run Trial before the final response, never after it. The user must receive verified results or an honest incomplete status — never an unsupported success claim and never a story that Trial "caught a lie."

Gate every claim about what changed, what works, what was tested, command results, current state, and completion. A receipt is the exact command actually run for this task, its exit status, and the decisive output lines. A reference to a test without a fresh run is not a receipt.

Coverage beats green. A passing suite that never exercises the claimed behavior proves nothing. Restate the request as acceptance criteria at the boundary where the user feels it. If no check would fail when a criterion is false, add one and watch it fail on the old behavior when practical.

Mandatory pre-delivery gate

  1. Frame — write testable acceptance criteria at the user-facing boundary.
  2. Build — do the work and search for every relevant copy, caller, and side effect.
  3. Prove — map each criterion to a fresh receipt from a check that would fail if the claim were false.
  4. Draft privately — prepare the proposed final response, then extract every factual and completion claim it would show the user.
  5. Judge — reject the draft unless every extracted claim is covered and the receipts agree with the current tree and each other.
  6. Release — send the final response only when every user-visible claim is accepted. Remove unsupported claims; never soften them into implied success.

Fail closed

  • ACCEPTED — release only the accepted claims and their concise receipts.
  • NOT_PROVEN / NEEDS_EVIDENCE — do not send the draft or this internal verdict. Continue working, run the missing proof, or remove the claim.
  • NEEDS_FIX — do not send the draft. Fix the defect, rerun the relevant checks, and judge a new draft.
  • ESCALATE — withhold completion. Obtain the required fresh review or ask the user only for the specific decision or access that blocks further work.

Read the full file on GitHub · 41 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. yesterday First seen · 41 lines · 45 tokens per session scan A a8047570f84e

Subscribe to this mod's changes

trial is a skill published in the GitHub repository Da7-Tech/trial (2 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 709 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

weave

Parallel strand orchestration — decompose a task into 3+ independently scoped strands, fan out real subagents (worktree-isolated when they write files), and coordinate through a session file and Insight Capsules. Use ONLY when the user explicitly invokes it by name or slash command.

entropyvortex/meta-llm-charter · 59 tokens

coding-agents-farm

To orchestrate parallel coding-agent farms (Claude, Codex, Copilot, Gemini, etc.) on isolated git worktrees.

griddynamics/rosetta · 32 tokens

mcp-media-inbox-triage

Find media, partnership, and high-intent requests buried in a shared Gmail inbox, summarize the useful ones, and route them to the right owner through Zapier MCP.

zapier/gtm-cheat-codes · 43 tokens

customer-deck-builder

Build tailored customer-facing sales or customer success decks from approved account context and generate the presentation with Gamma through Zapier MCP.

zapier/gtm-cheat-codes · 29 tokens

premortem

First-principles premortem on a high-stakes plan: assume failure 6–18 months out, reconstruct causal death chains, surface hidden assumptions, deliver a revised reversibility-weighted plan. Use ONLY when the user explicitly invokes it by name or slash command.

entropyvortex/meta-llm-charter · 59 tokens

zero-pause

Continuous-momentum execution mode — no artificial phases, pre-work questions only, human-gated items parked in humanpending.md while non-dependent work ships. Use ONLY when the user explicitly invokes it by name or slash command.

entropyvortex/meta-llm-charter · 48 tokens