Trust Decay

Trust Decay is a skill for Claude Code, Codex from wrg32786/aigent-os. It costs 78 tokens per session (1,142 once invoked), scanned A, original, MIT.

A two-stage record of confident claims made by an agent and the later evidence showing whether each claim was right or wrong. It is designed for tracking accuracy over time.

In plain words
What is it for?
Use it to log consequential agent claims and resolve them after testing, user checks, or a returning bug.
Why use it?
It makes unverified statements such as “fixed” or “complete” easier to review when later results reveal mistakes or confirm them.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to log consequential agent claims and resolve them after testing, user checks, or a returning bug.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wrg32786/aigent-os/trust-decay
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.

Any agent
npx skills add wrg32786/aigent-os --skill trust-decay
Clone the repo
git clone --depth 1 https://github.com/wrg32786/aigent-os

Made for: Claude Code, Codex.

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 Decay

README.md
[![agentmods](https://agentmods.dev/badge/skills/wrg32786/aigent-os/trust-decay/github.svg)](https://agentmods.dev/skills/wrg32786/aigent-os/trust-decay)
Your own site
<a href="https://agentmods.dev/skills/wrg32786/aigent-os/trust-decay"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/trust-decay/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.

agentmods 80×15 button for Trust Decay

Your own site · 80×15
<a href="https://agentmods.dev/skills/wrg32786/aigent-os/trust-decay"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/trust-decay.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,142 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00078 $0.01142
Opus 5 $0.00039 $0.00571
Sonnet 5 $0.00016 $0.00228
Haiku 4.5 $0.00008 $0.00114

Measured 9d ago against content hash 9fe939cb2ddd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

Trust Decay 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 9d 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.

skills/trust-decay/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trust Decay

The two-phase ledger that tracks confident agent claims and their eventual outcomes. See [[Cost of Confidence]] for the doctrine.

When to use

Phase 1 — Capture a confident claim

  • An agent declared something "fixed", "tested", "verified", "complete", "deployed"
  • The claim is unhedged or treated as ground truth
  • The claim is consequential enough that being wrong about it would matter
  • Triggered by Caddy on prompts like: "/trust-decay capture", "log this claim", "capture confidence", "agent claimed", "I claimed", "the agent said it was fixed", "another agent verified"

Phase 2 — Resolve a claim

  • A previously-captured claim has been confirmed (right) or revealed wrong
  • The principal noticed a discrepancy between an earlier claim and reality
  • Triggered by Caddy on prompts like: "/trust-decay resolve", "the bug came back", "that wasn't actually fixed", "trust event", "wrong claim", "confidence was wrong"

How to execute

Phase 1 — Capture

## YYYY-MM-DD — {short claim summary}
**Claim:** "{the actual confident statement, verbatim}"
**Source:** {agent name or self}
**Context:** {what task, what session, what was being worked on}
**Verification stated:** {what the claimant said they verified, if anything}
**Status:** OPEN — awaiting outcome

Append to vault/memory/TRUST_DECAY.md under the "Open" section.

The principal can capture manually, OR /honesty-check (when wired) can auto-capture any unhedged confident claim it produces.

Phase 2 — Resolve

When a previously-captured claim is proved or disproved:

  1. Find the open entry in vault/memory/TRUST_DECAY.md matching the claim
  2. Append resolution data:
**Resolution (YYYY-MM-DD):** WRONG | PARTIALLY WRONG | CONFIRMED CORRECT
**Evidence:** {what surfaced the discrepancy — file/line/log/observation}
**Time-to-discovery:** {duration from claim to discovery}
**Trust-decay event:** YES | NO
**Pattern:** {one line — what category of mistake/correctness was this?}

Read the full file on GitHub · 107 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. 9d ago First seen · 107 lines · 78 tokens per session scan A 9fe939cb2ddd

Subscribe to this mod's changes

Trust Decay is a skill published in the GitHub repository wrg32786/aigent-os (18 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 1,142 once invoked, about $0.0004 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 2026-09-03.