source-health

source-health is a skill for Claude Code from gtapps/claude-code-hermit. It costs 71 tokens per session (1,453 once invoked), scanned A, original, MIT.

A read-only report that reviews how well configured news sources perform across recent briefs. It checks whether sources provided items, failed to fetch, or returned nothing.

In plain words
What is it for?
Use it to inspect quiet and skipped source streaks and review fetching cost efficiency.
Why use it?
It helps find sources that repeatedly waste fetching effort without contributing useful material.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the feed-hermit plugin — 7 skills, 1 agent shipped together

Good fit Use it to inspect quiet and skipped source streaks and review fetching cost efficiency.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gtapps/claude-code-hermit/source-health
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 gtapps/claude-code-hermit --skill source-health
Clone the repo
git clone --depth 1 https://github.com/gtapps/claude-code-hermit

Made for: Claude Code.

Or install feed-hermit, the plugin that ships this one along with the rest of its 7 skills, 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 source-health

README.md
[![agentmods](https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/source-health.svg)](https://agentmods.dev/skills/gtapps/claude-code-hermit/source-health)
Your own site
<a href="https://agentmods.dev/skills/gtapps/claude-code-hermit/source-health"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/source-health.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,453 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 $0.00071 $0.01453
Opus 5 $0.00036 $0.00727
Sonnet 5 $0.00014 $0.00291
Haiku 4.5 $0.00007 $0.00145

Measured 3d ago against content hash 952918e46d88, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

source-health 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 3d 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/feed-hermit/skills/source-health/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Source Health

Read-only audit of brief source performance. Scans recent briefs and flags underperforming sources before they silently waste fetch budget.

When to use

  • Manually, to spot-check source health.
  • Wired into weekly review to catch slow-building problems.
  • After adding a new source, to confirm it's yielding items.

Steps

  1. Read feed-sources.md — extract the active source names (Name column).

  2. Glob briefs — list .claude-code-hermit/briefs/*.md, sort descending by filename (newest first), take the last N = 10 (override with --last N).

  3. Parse each brief's frontmatter — extract:

    • sources_used: sources that contributed ≥1 item.
    • sources_skipped: sources that failed to fetch (network error, Chrome unavailable, script error).
    • sources_quiet: sources that fetched cleanly but yielded 0 items.
    • fetch_log: per-source efficiency array (may be absent in older briefs — treat as missing, not an error).

    If a source appears in none of the three arrays, mark it unknown for that brief (may predate the schema).

  4. Compute per-source streaks — walking newest→oldest for each active source:

    • consecutive_quiet: consecutive briefs the source was in sources_quiet.
    • consecutive_skipped: consecutive briefs the source was in sources_skipped.
    • Reset the streak when the source appears in sources_used or is unknown.
  5. Flag threshold violations — any source where consecutive_quiet >= 3 OR consecutive_skipped >= 3.

  6. Output a health table:

    ## Source Health — YYYY-MM-DD (last 10 briefs)
    
    | Source                | Last 10 (newest→oldest)    | Streak       | Status    |
    |-----------------------|----------------------------|--------------|-----------|
    | Source A              | ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓      | —            | healthy   |
    | Source B              | ~ ~ ~ ✓ ~ ~ ~ ✓ ~ ~       | 3 quiet      | ⚠ warn    |
    | Source C              | ✗ ✗ ✗ ✗ ✓ — — — — —      | 4 skipped    | ✗ flag    |
    

    Legend: contributed · ~ quiet (fetched, nothing relevant) · skipped (fetch failed) · not yet in sources or brief predates schema.

Read the full file on GitHub · 110 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. 3d ago First seen · 110 lines · 71 tokens per session scan A 952918e46d88

Subscribe to this mod's changes

source-health is a skill published in the GitHub repository gtapps/claude-code-hermit (74 stars, last pushed today), licensed MIT. It adds 71 tokens to every session and 1,453 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.