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/bundlenpx skills add alivecontext/alive --skill bundlegit 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 | $0.00034 | $0.02548 |
| Opus 5 | $0.00017 | $0.01274 |
| Sonnet 5 | $0.00007 | $0.00510 |
| Haiku 4.5 | $0.00003 | $0.00255 |
Grade A, and why
alive:bundle 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 — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bundle
Manage the bundle lifecycle: create, share, graduate, status. Bundles are the unit of focused work — anything with a deliverable or a future audience.
This skill is invoked by the bundle awareness injection, by the load skill's "what are you working on?" prompt, or directly by the human via /alive:bundle.
Detection — When to Invoke
The spectrum:
| One-off | Bundle | Walnut | |
|---|---|---|---|
| Sessions | This session only | Likely >1, or worth returning to | Own ongoing lifecycle |
| Deliverable | No | Yes — ship, send, or reference later | Multiple deliverables |
| Audience | Just you, right now | Someone specific, or future-you | Has its own people |
Trigger: "Does this have a deliverable or a future audience?" If yes -> bundle.
Bundle Types
Outcome Bundle
The default. A body of work with a deliverable — a document, a plan, a shipped feature. Has drafts, versions, a finish line.
Evergreen Bundle
Living reference material that grows over time. No "done" state — it accumulates. Research collections, style guides, knowledge bases. Status cycles between active and maintaining rather than progressing to done.
Bundle Location
Bundles live flat in the walnut root. A folder is a bundle if it contains context.manifest.yaml.
nova-station/ # walnut root
_kernel/
shielding-review/ # bundle
context.manifest.yaml
raw/
launch-checklist/ # another bundle
context.manifest.yaml
raw/
No bundles/ subdirectory. Every bundle sits directly in the walnut root alongside _kernel/.
Operations
Create
When no active bundle matches the current work:
- Ask for the goal — one sentence. "What are you building?"
- Determine bundle type — outcome (default) or evergreen
- Derive the bundle name from the goal (kebab-case, descriptive)
- Confirm:
╭─ 🐿️ new bundle
│
│ Name: shielding-review
│ Type: outcome
│ Walnut: nova-station
│ Goal: Evaluate radiation shielding vendors for habitat module
│ Path: shielding-review/
│
│ ▸ Good?
│ 1. Create
│ 2. Change name
│ 3. Make it evergreen instead
│ 4. Cancel
╰─
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 · 318 lines · 34 tokens per session scan A 7d9865235c9e
alive:bundle is a skill published in the GitHub repository alivecontext/alive (127 stars, last pushed 6d ago), licensed MIT. It adds 34 tokens to every session and 2,548 once invoked, about $0.0002 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
crit-cli
Use when an agent needs to author or reply to crit inline comments programmatically (including multi-agent workflows commenting on shared code/plans/docs/proposals), publish or unpublish a crit review with crit share, sync a crit review to or from a GitHub PR or GitLab MR, or read/interpret a crit review JSON file.…
crit
Review code changes, a plan, a live page (running dev server), or a local HTML file with Crit inline comments and structured human feedback. Use only when the user explicitly invokes /crit or directly asks to use Crit; a generic review request does not count.
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.
cco-config
View and tune CCO's behavior thresholds — re-read warnings, cache staleness, prompt-coach length bands, and the /cco-pack budget cap.
cco-budget
Configure token budget limits, auto-compact settings, and view current budget status (model-aware — Opus 4.8 default, full 1M context at standard price).
cco-patterns
Share learned file patterns across a team — export an anonymized digest of what's usually waste/useful/co-edited, and import a teammate's so a fresh clone benefits day one.