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.
npx skills add gtapps/claude-code-hermit --skill source-scoutgit clone --depth 1 https://github.com/gtapps/claude-code-hermitWrote 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.
[](https://agentmods.dev/skills/gtapps/claude-code-hermit/source-scout)<a href="https://agentmods.dev/skills/gtapps/claude-code-hermit/source-scout"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/source-scout.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00077 | $0.01147 |
| Opus 5 | $0.00039 | $0.00574 |
| Sonnet 5 | $0.00015 | $0.00229 |
| Haiku 4.5 | $0.00008 | $0.00115 |
Grade A, and why
source-scout 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Source Scout
Proactively discover and add new RSS/web sources to feed-sources.md. Complements source-health
(removal) with discovery (addition). Can run on a schedule via scheduled_checks.
Flags
--scheduled: invoked by a scheduled check (non-interactive, no operator present). The security rule restricting automated WebFetch to domains already infeed-sources.mdmeans the step-3 verification fetch cannot run — candidates are queued unverified for operator review instead of being auto-added.- No flag (default): interactive/on-demand (operator ran
/source-scout). Full behavior — verify and auto-add — since the operator's live presence satisfies the security rule's intent.
Steps
-
Read current state (in parallel):
feed-sources.md— extract active source names, URLs, categories. Count sources per category.feed-categories.md— all P1/P2 categories and their priorities.- Glob
.claude-code-hermit/compiled/story-arcs-*.md, read the most recent. Extract Watch-clause keywords from each active arc under## Active.
-
Identify gaps:
- Any P1 or P2 category with fewer than 3 active sources is a gap category.
- Active story arcs with Watch keywords that no current source covers by name/domain are arc gaps.
- No gaps → log
source-scout: no gaps foundto SHELL.md Findings and stop.
-
Discover candidates (up to 3 total across all gaps). Use WebSearch to find RSS feeds — for a category gap, search for RSS feeds / newsletters covering that category; for an arc gap, search for feeds covering the arc's Watch keywords.
No flag (interactive): for each candidate, verify the feed URL with WebFetch (valid RSS/Atom XML). Discard any that 404 or return non-feed content.
--scheduled: do NOT WebFetch candidate URLs — they are not yet infeed-sources.md, so an automated fetch would violate the domain-allowlist rule. Collect candidates from WebSearch results as-is (name, URL, gap addressed, why it surfaced), explicitly marked unverified. Skip to step 4.
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.
- 3d ago First seen · 80 lines · 77 tokens per session scan A 96e0265ef6a2
source-scout is a skill published in the GitHub repository gtapps/claude-code-hermit (74 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 1,147 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.
Other skills, from other repositories
plan-to-tasks
Transform a plancreation planv{N}.md into a structured tasks.yaml + per-WP workpackages/.yaml using parallel Sonnet sub-agents. Use after plan-creation finishes when you need execution-friendly task structure.
debt-ops-add
Register a deferred decision in the tech-debt registry. Trigger by judgment, not a marker scan, whenever a future reader would ask "why this way?": an unmade decision, stub, loosened type, bypassed check, swallowed error, a default picked "for now", or a TODO/FIXME/HACK/XXX marker. Trigger immediately whenever you…
ccc-onboard
CC Commander contributor onboarding workflow. Detects project conventions, asks for contributor role, builds a tailored first-hour checklist, starter links, and…
ccc-broadcast
Relay CC Commander build, deploy, CI, task, and cost signals to your team's chat or email so non-devs see what shipped — read-only, no secrets in payloads.
ccc-linear
Linear board integration — view open issues, pick one to work on, or create new tickets without leaving Claude. Use when the user types $ccc-linear, /ccc linear, says…
import
Import a tasks.md into the coco tracker as an epic with dependencies, and create matching issues in the configured issue tracker.