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 weekly-digestgit 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/weekly-digest)<a href="https://agentmods.dev/skills/gtapps/claude-code-hermit/weekly-digest"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/weekly-digest.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00072 | $0.01530 |
| Opus 5 | $0.00036 | $0.00765 |
| Sonnet 5 | $0.00014 | $0.00306 |
| Haiku 4.5 | $0.00007 | $0.00153 |
Grade A, and why
weekly-digest 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Weekly Digest
Produce a weekly synthesis from the archived brief notes. All data comes from
.claude-code-hermit/briefs/ — no re-fetching of sources. Cheap to run.
Steps
-
Read the week's briefs. Glob
.claude-code-hermit/briefs/*.md(exclude theweekly/subdirectory), then filter to files whose filename date prefix falls within the past 7 days (today minus 6 days through today). Read each matching file (frontmatter + body).- Directory absent or empty → deliver "No briefs archived this week." and stop.
- Fewer than 3 briefs → note the gap, produce the digest from whatever is available.
- Track the actual count of files read — this is
brief_countfor the archive.
-
Synthesize content. From the brief bodies:
- Top stories — items appearing across multiple briefs or escalating in coverage. Cite which day(s) they appeared.
- Emerging themes — topics absent early in the week that dominated late in the week.
- Faded stories — topics in ≥2 consecutive early-week briefs that appear in no late-week brief. Surface at most 2; omit the section if none meet the threshold.
- Category activity — count items per category directly from brief bodies across all briefs. Do NOT use
top_categoriesfrontmatter for this tally — it is pre-truncated to top 5 per brief and undercounts categories that consistently rank below the cutoff.
-
Source performance. Read
feed-sources.mdfor the full source list, then from frontmatter across the week:- Reliable sources — appeared in
sources_usedin ≥5 briefs. - Unreliable sources — appeared in
sources_skippedmore often thansources_used. Include the skip count (e.g. "Source X (skipped 8/12 briefs)"). - Silent sources — in
feed-sources.mdbut in neithersources_usednorsources_skippedacross any brief this week (may never have been attempted). Keep to 3–5 bullets, actionable framing. sources_skipped(fetch failures) is the reliability signal.sources_quiet(0 items on a quiet day) is NOT — never count quiet days against a source's reliability.
- Reliable sources — appeared in
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 · 99 lines · 72 tokens per session scan A 75678d7857ca
weekly-digest is a skill published in the GitHub repository gtapps/claude-code-hermit (74 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 1,530 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
cco-tools
Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses.
github-pr-creation
Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…
design-system-reference
Style guides and implementation rules for frontend design. Works with design-discovery agent which handles context gathering and VS-based style recommendations. Contains detailed style guides, anti-patterns, and implementation checklists.
magic-compact
Compact this Claude Code session.
boss-briefing
Vault health check — workflow pattern analysis, profile sync, session gap recovery, persona rule proposals.
subagent-output-templating
Template for structured sub-agent output including YAML log format, task completion reports (WHY/WHAT/TRADE-OFFS/RISKS), and summary constraints. Use when defining how sub-agents should report results.