Borrowing it
Nothing to install: this file belongs to acartine/foolery. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/acartine/foolery/main/.agents/skills/knots-e2e/SKILL.mdgit clone --depth 1 https://github.com/acartine/fooleryWrote 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/acartine/foolery/knots-e2e)<a href="https://agentmods.dev/skills/acartine/foolery/knots-e2e"><img src="https://agentmods.dev/badge/skills/acartine/foolery/knots-e2e/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/acartine/foolery/knots-e2e"><img src="https://agentmods.dev/badge/skills/acartine/foolery/knots-e2e.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00068 | $0.01235 |
| Opus 5.5 | $0.00027 | $0.00494 |
| Sonnet 5.5 | $0.00014 | $0.00247 |
| Haiku 4.5 | $0.00007 | $0.00123 |
Grade A, and why
knots-e2e 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 2mo 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knots E2E
Agent identity
Create or receive a lease before the first claim:
kno lease create --nickname "<session-name>"
Bind the same lease to every e2e claim, advance, note, and handoff-capsule command in the run. Agent identity for notes, handoff capsules, state transitions, and gate decisions comes from the bound lease.
Do not copy legacy --*-agentname/model/version identity flags from telemetry
or command history. They are deprecated, ignored by current kno, and can
leave metadata attributed as [unknown <date>] when no lease is bound.
Invocation precedence
When this skill is invoked, the agent MUST claim with the --e2e flag so the
workflow boundary surfaced by kno advertises e2e-continuation semantics
rather than the default single-action boundary:
kno claim --e2e <id> --lease <lease-id>
The claim output will then carry kind: e2e_continuation in the workflow
boundary section (and "workflow_boundary_kind": "e2e_continuation" plus
"e2e": true in --json output). That signal authorizes the agent to keep
working past the per-claim "complete exactly one workflow action" boundary
that ordinary claims emit. After every successful kno next, immediately
re-claim with kno claim --e2e <id> --lease <lease-id> and continue until the
knot reaches SHIPPED, BLOCKED, or DEFERRED.
If the claim output shows kind: single_action (i.e. --e2e was not
passed), do NOT continue past the boundary. Stop after the single action
and ask the user to re-invoke with the e2e skill if they want to continue.
Workflow
Follow this sequence:
kno claim --e2e <id> --lease <lease-id>
- If you are working inside a git worktree, run Knots commands as
kno -C <path_to_repo> ...because Knots is installed for the repo root, not the worktree path. - Record the current state from the claim output.
- If the current state is
SHIPPED,BLOCKED, orDEFERRED, stop cleanly. - Use the claim output to determine the current state's completion goals.
- Do the work and validate it.
- If the goals were met, advance with a guarded state check:
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.
- 2mo ago First seen · 129 lines · 68 tokens per session scan A 9d7d2f918e44
knots-e2e is a skill published in the GitHub repository acartine/foolery (60 stars, last pushed 13d ago), licensed MIT. It adds 68 tokens to every session and 1,235 once invoked, about $0.0003 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 2026-08-30.
knots-e2e compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| knots-e2eacartine/foolery | Skill | 60 | 13d ago | MIT | A | 68 | Claude Code, Codex |
| lavra-ceo-reviewroberto-mello/lavra | Skill | 53 | 15d ago | MIT | A | 27 | Claude Code |
| lavra-reviewroberto-mello/lavra | Skill | 53 | 15d ago | MIT | A | 15 | Claude Code |
| dspy-rubyroberto-mello/lavra | Skill | 53 | 15d ago | MIT | A | 35 | Claude Code |
| lavra-brainstormroberto-mello/lavra | Skill | 53 | 15d ago | MIT | A | 15 | Claude Code |
| lavra-eng-reviewroberto-mello/lavra | Skill | 53 | 15d ago | MIT | A | 19 | Claude Code |
| write-documentationDollarDill/beads-superpowers | Skill | 32 | 6d ago | MIT | A | 56 | Claude Code |