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/hermitd --skill downstream-impactgit clone --depth 1 https://github.com/gtapps/hermitdWrote 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/hermitd/downstream-impact)<a href="https://agentmods.dev/skills/gtapps/hermitd/downstream-impact"><img src="https://agentmods.dev/badge/skills/gtapps/hermitd/downstream-impact/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.
<a href="https://agentmods.dev/skills/gtapps/hermitd/downstream-impact"><img src="https://agentmods.dev/badge/skills/gtapps/hermitd/downstream-impact.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00170 | $0.01128 |
| Opus 5.5 | $0.00068 | $0.00451 |
| Sonnet 5.5 | $0.00034 | $0.00226 |
| Haiku 4.5 | $0.00017 | $0.00113 |
Grade A, and why
downstream-impact 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- downstream-impact — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Downstream Impact
The question behind every invocation: if this ships, what does a hermit running on someone else's box do differently, and what does the person chatting with it notice? Not the diff, not the architecture. The reader is the maintainer deciding whether a change is worth shipping, how to word the changelog, or how to explain it to an operator on Discord.
Read-only. Never edits, commits, or releases.
Usage
/downstream-impact— the change under discussion in this conversation; otherwisegit diff main...HEADplus the working tree; on a cleanmain, every plugin's[Unreleased]section./downstream-impact <PR number>—gh pr diff <N>and the PR body./downstream-impact <branch>— that branch againstmain./downstream-impact <plan file>— the plan's steps, before anything is built./downstream-impact "<described change>"— a change that exists only as an idea; label every claim as assumed.
Step 1 — Locate the touchpoints
A change reaches downstream only through a few surfaces. Read only what the diff (or plan) touches and check each surface:
- Operator chat: channel notices, push notifications,
AskUserQuestionprompts, skill text that composes messages. Does the operator see new, fewer, or differently worded messages? Is there a new thing they can ask for? - Hermit flow: hooks, heartbeat, routines, watches, watchdog, session start/close. Does the hermit wake more, less, or for a different reason? Did a step move from the model to a script, or the reverse?
- Upgrade path:
templates/, migrations,### Upgrade Instructions. What doeshermit-evolverewrite, what does the operator do by hand, what operator-edited file survives. - Gates:
min_claude_code_version,required_core_version, new config keys, permission or deny rules, default on or off. Who is excluded, who has to opt in. - Cost: per-wake context, hook stdout, new always-loaded text.
- Reach:
mainis staging. Installed operators see nothing until the plugin'sversionbumps;--plugin-dirtesters and fresh installs seemainHEAD. Say which group this reaches today.
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.
- 11d ago First seen · 52 lines · 170 tokens per session scan A b1fe9f4d15a5
downstream-impact is a skill published in the GitHub repository gtapps/hermitd (79 stars, last pushed today), licensed MIT. It adds 170 tokens to every session and 1,128 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-10-02.
Other skills, from other repositories
apex-review
Cross-cutting review of recent work — catches gaps between specialists. Use when asked to "review what we built", "check the work", "pre-launch review", or after completing a significant chunk of work.
spine-review
API and backend code review — REST conventions, auth, validation, error handling, pagination, rate limiting, test coverage. Use when asked to "review this API", "code review", "review backend", or "pre-launch backend check".
github-pr-review
Handles PR review comments and feedback resolution. Use when user wants to resolve PR comments, handle review feedback, fix review comments, address PR review, check review status, respond to reviewer, verify PR readiness, review PR comments, analyze review feedback, evaluate PR comments, assess review suggestions, or…
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…
superreview
Review a change set or explicit project scope for intent, correctness, safety, reuse, and maintainability; independently validate findings and produce one report without applying fixes.
init
Opt-in onboarding for the mARC agent team. Scaffolds a per-repo team binding so the team graduates from ephemeral session-memory to persistent, versioned config — without ever writing a file silently. Discovers the repo's org/repo/ project at runtime via gh, prefills {{ agentsdir }}/team.toml, and (optionally) a lean…