no-silent-pass

no-silent-pass is a skill for Claude Code from AleksandarBisevac/claude-plugins. It costs 143 tokens per session (2,802 once invoked), scanned A, original, MIT.

A set of rules for making Python programs and checks show failures clearly instead of producing normal-looking results when something went wrong. Its self-tests are cases built into each file and report how many passed.

In plain words
What is it for?
Use it when handling exceptions, defaults, invalid input, subprocess results, or self-tests, particularly in code that processes records or reports status.
Why use it?
It prevents failed operations from being mistaken for success and prevents tests that assert nothing from appearing to pass. This makes errors and incomplete results visible to both people and automation.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it when handling exceptions, defaults, invalid input, subprocess results, or self-tests, particularly in code that processes records or reports status.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aleksandarbisevac/claude-plugins/no-silent-pass
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 AleksandarBisevac/claude-plugins --skill no-silent-pass
Clone the repo
git clone --depth 1 https://github.com/AleksandarBisevac/claude-plugins

Made for: Claude Code.

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 no-silent-pass

README.md
[![agentmods](https://agentmods.dev/badge/skills/aleksandarbisevac/claude-plugins/no-silent-pass/github.svg)](https://agentmods.dev/skills/aleksandarbisevac/claude-plugins/no-silent-pass)
Your own site
<a href="https://agentmods.dev/skills/aleksandarbisevac/claude-plugins/no-silent-pass"><img src="https://agentmods.dev/badge/skills/aleksandarbisevac/claude-plugins/no-silent-pass/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 no-silent-pass

Your own site · 80×15
<a href="https://agentmods.dev/skills/aleksandarbisevac/claude-plugins/no-silent-pass"><img src="https://agentmods.dev/badge/skills/aleksandarbisevac/claude-plugins/no-silent-pass.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 143 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,802 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.
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 $0.00143 $0.02802
Opus 5 $0.00072 $0.01401
Sonnet 5 $0.00029 $0.00560
Haiku 4.5 $0.00014 $0.00280

Measured 11d ago against content hash 807bcd5f47d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

no-silent-pass 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 11d 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.

.claude/skills/no-silent-pass/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

No silent pass

Two halves of one rule. Code must not produce normal-looking output when something went wrong, and a check must not look green while asserting nothing. Both fail the same way: everything reports fine and nobody learns anything for months.

This repo's test suite is the --selftest block inside each file, printing N/M cases passed. Everything below is about those cases and the code they guard.

Fail loud

  • Give success and failure distinct sentinels. If the error path writes the same value the success path writes, failed runs read as complete. except Exception: status = "READY" is the shape to look for.
  • When you catch, either recover meaningfully or make the failure visible — raise, or return a distinguishable value. A return/continue/fallback inside except that produces normal-shaped output is where silent corruption lives.
  • x = x or default is a bug whenever 0, False or "" are meaningful. Use x if x is not None else default. Reserve the or form for empty containers.
  • A no-op on unexpected input is silent corruption. Skipping a key you do not recognise, or continue-ing past a record you cannot parse, with no error and no count, leaves the caller believing the operation applied.
  • Filtering down to empty must never read as "all clear." When a selector, rule set or work list narrows to nothing, an "evaluated everything, found no problems" path reports a perfect result while checking nothing. Say that the set was empty.
  • Validate every precondition before the first mutation. A write that half-applies and then raises leaves the caller's state corrupted even though the exception was correct. Where that is not possible, stage on a copy and commit after.
  • Do not discard the real output on a non-zero exit. A runner that returns only stderr when returncode != 0 loses the answer for tools that exit non-zero by design and write their result to stdout — which is exactly what this repo's own validators and gates do.
  • Impose a total order before serializing. Iterating a set emits a different order per process, so a regenerated file is the same data reshuffled and the real change drowns in noise.

Read the full file on GitHub · 189 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. 11d ago First seen · 189 lines · 143 tokens per session scan A 807bcd5f47d9

Subscribe to this mod's changes

no-silent-pass is a skill published in the GitHub repository AleksandarBisevac/claude-plugins (4 stars, last pushed 2d ago), licensed MIT. It adds 143 tokens to every session and 2,802 once invoked, about $0.0007 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.