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 agentmods add skills/alivecontext/alive/feedbacknpx skills add alivecontext/alive --skill feedbackgit clone --depth 1 https://github.com/alivecontext/aliveWhat 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 | $0.00054 | $0.01918 |
| Opus 5 | $0.00027 | $0.00959 |
| Sonnet 5 | $0.00011 | $0.00384 |
| Haiku 4.5 | $0.00005 | $0.00192 |
Grade A, and why
alive:feedback 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 2d 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feedback
Send feedback to the ALIVE team. Bug reports, feature requests, general thoughts — whatever is on your mind.
Nothing personal leaves your machine. The only content in the issue is what you type plus anonymous system metadata (plugin version, model, OS). No walnut data, no file contents, no conversation history.
Flow
1. Ask Type
╭─ 🐿️ feedback
│
│ ▸ What kind?
│ 1. Bug report
│ 2. Feature request
│ 3. General feedback
╰─
2. Collect Description
Based on type, prompt with guidance that encourages detail:
- Bug: "What went wrong? What did you expect to happen? Include any error messages you saw — the more detail, the better our chance of fixing it."
- Feature: "What would you like to see? How would you use it? Help us understand the problem you're solving."
- General: "What's on your mind? The more context you give, the more useful it is for us."
The human types their message. Free text, no template.
For bugs only, ask one follow-up: "What did you expect to happen instead?"
3. Detect Skill Context
Check if an /alive:* skill was invoked earlier in this session. If so, offer to include it:
╭─ 🐿️ context
│ Looks like you were using alive:save
│
│ ▸ Include that as context?
│ 1. Yes
│ 2. No
╰─
If no skill was recently invoked, skip this step silently.
4. Optional Attach
Surface available diagnostic context one item at a time. Each requires individual consent.
Error output (any type): If recent tool errors or hook failures occurred in this session, offer regardless of feedback type:
╭─ 🐿️ diagnostics
│ There were errors earlier in this session.
│
│ ▸ Include the error output? (helps us diagnose)
│ 1. Yes, include it
│ 2. No, skip
╰─
Walnut name (bugs only): If a walnut is loaded and the type is bug, offer:
╭─ 🐿️ diagnostics
│ You're working in a walnut right now.
│
│ ▸ Include the walnut name? (just the name, nothing else)
│ 1. Yes
│ 2. No
╰─
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.
- 2d ago First seen · 257 lines · 54 tokens per session scan A b11c2cc8d97b
alive:feedback is a skill published in the GitHub repository alivecontext/alive (127 stars, last pushed 7d ago), licensed MIT. It adds 54 tokens to every session and 1,918 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
cco-task
Organize work by task and track tokens/cost per task — start a task, list tasks, or mark the active one done. Pairs with /cco-pack to load minimal context per task.
backlog-technical-project-manager
Technical project management for Backlog.md workstreams using coordinated sub-agents. Use only when the user explicitly asks Codex to take over one or more existing Backlog.md tasks (for example: "act as TPM", "coordinate these tasks", "delegate to sub-agents"). Orchestrate planning, implementation, and finalization…
omh-agent-board
This is a Hermes-native agent-board workflow skill.
omh-idea-to-deploy
This is a Hermes-native idea-to-deploy workflow skill.
triage-sweep
Backfill labels across oh-my-hermes issues and pull requests. Run manually to sweep everything currently unlabeled, or pass a number to triage one item. Use when issues and PRs have accumulated without labels, after adding a new label to .github/labels.yml, or before a release when the backlog needs to be readable by…
crit-story
Author a crit story only when the user explicitly invokes /crit-story or directly asks you to generate a crit story. Do not infer this skill from generic review, PR, or diff-review requests.