trust

trust is a skill for Claude Code from alicicek/tale-mode. It costs 118 tokens per session (1,097 once invoked), scanned A, original, MIT.

A guide to the two user-controlled opt-in files that authorize tale-mode gate behavior. It explains content hashes, home-directory trust files, and the exact commands the user can choose to run.

In plain words
What is it for?
Use it when reviewing or trusting a repository's tale-mode gates, understanding the security model, or learning about the Codex working-directory opt-in.
Why use it?
It prevents a repository or agent from silently granting itself permission to execute committed shell commands. Changes to trusted gate content also invalidate that trust.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

Part of the tale-mode plugin — 6 skills, 2 commands, 1 agent shipped together

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/alicicek/tale-mode/trust
Any agent
npx skills add alicicek/tale-mode --skill trust
Clone the repo
git clone --depth 1 https://github.com/alicicek/tale-mode

Made for: Claude Code.

Or install tale-mode, the plugin that ships this one along with the rest of its 6 skills, 2 commands, 1 agent.

Wrote 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.

agentmods badge for trust

README.md
[![agentmods](https://agentmods.dev/badge/skills/alicicek/tale-mode/trust.svg)](https://agentmods.dev/skills/alicicek/tale-mode/trust)
Your own site
<a href="https://agentmods.dev/skills/alicicek/tale-mode/trust"><img src="https://agentmods.dev/badge/skills/alicicek/tale-mode/trust.svg" alt="Measured on agentmods" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,097 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 5.1 $0.00118 $0.01097
Opus 5 $0.00059 $0.00549
Sonnet 5 $0.00024 $0.00219
Haiku 4.5 $0.00012 $0.00110

Measured 6d ago against content hash c34dae832ab3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

trust 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 6d 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.

plugins/tale-mode/skills/trust/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trusting tale-mode's gates and opt-ins

tale-mode's Stop-hook loop has two separate user-only grant files, both living in the user's home (never in a repo). Your job with this skill is to explain them and hand the user the exact commands — never to run those commands yourself. Writing either file is the user's deliberate act; an agent (or a cloned repo) doing it on their behalf defeats the security model.

1. The committed-gate trust store — ~/.claude/tale-mode-trust

What it gates. A repo may commit .claude/tale-mode.json with a gates list (arbitrary shell, each entry running as one script). During a deliberate kickoff phase with uncommitted changes, the Stop hook (hooks/stop-goal-loop.sh) runs those gates and blocks the turn until they're green — but only if the file's exact content-hash is listed in the trust store. No listed hash → the gates never execute; the hook instead shows a one-time "review and trust" notice containing the hash.

Why a content-hash. Trusting the content (not the path) means any edit to the config — including a malicious gate slipped into a pull — invalidates the trust and the gates go inert until the user re-reviews and re-trusts the new hash.

How the user grants it (after actually reading the gates in .claude/tale-mode.json):

shasum -a 256 .claude/tale-mode.json     # macOS; on Linux: sha256sum .claude/tale-mode.json
echo "<that-hash>  # <repo-name> tale-mode gates" >> ~/.claude/tale-mode-trust

One hash per line; anything after whitespace is a comment. Revoke by deleting the line. The store path can be overridden with TALE_TRUST_STORE (used by the test suites).

Hard rule (D3): the hook and the agent only ever read this store. If you (the agent) are asked to "just trust it," decline and show the commands — the user reviews the gates, the user writes the line. A repo whose gates self-trust is exactly the attack this design prevents.

2. The Codex cwd-root opt-in — ~/.tale-mode-allow-cwd-root

Read the full file on GitHub · 79 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. 6d ago First seen · 79 lines · 118 tokens per session scan A c34dae832ab3

Subscribe to this mod's changes

trust is a skill published in the GitHub repository alicicek/tale-mode (36 stars, last pushed 2mo ago), licensed MIT. It adds 118 tokens to every session and 1,097 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 2026-08-30.

Related

Other skills, from other repositories

recipe-reverse-engineer

Generate PRD and Design Docs from existing codebase through discovery, generation, verification, and review workflow.

shinpr/claude-code-workflows · 26 tokens

recipe-front-review

Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.

shinpr/claude-code-workflows · 29 tokens

new-skill

Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…

hyhmrright/brooks-lint · 145 tokens

brooks-sweep

Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…

hyhmrright/brooks-lint · 178 tokens

brooks-test

Test quality review drawing on twelve classic engineering books — with primary focus on xUnit Test Patterns, The Art of Unit Testing, How Google Tests Software, and Working Effectively with Legacy Code — that diagnoses structural problems in an existing test suite: brittleness, mock abuse, coverage illusions, slow…

hyhmrright/brooks-lint · 161 tokens

recipe-add-integration-tests

Add integration/E2E tests to existing codebase using Design Docs.

shinpr/claude-code-workflows · 19 tokens