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 bahayonghang/my-ai-cli-toolkit --skill trellis-plan-reviewgit clone --depth 1 https://github.com/bahayonghang/my-ai-cli-toolkitWrote 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/bahayonghang/my-ai-cli-toolkit/trellis-plan-review)<a href="https://agentmods.dev/skills/bahayonghang/my-ai-cli-toolkit/trellis-plan-review"><img src="https://agentmods.dev/badge/skills/bahayonghang/my-ai-cli-toolkit/trellis-plan-review/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/bahayonghang/my-ai-cli-toolkit/trellis-plan-review"><img src="https://agentmods.dev/badge/skills/bahayonghang/my-ai-cli-toolkit/trellis-plan-review.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 | $0.00184 | $0.02189 |
| Opus 5 | $0.00092 | $0.01094 |
| Sonnet 5 | $0.00037 | $0.00438 |
| Haiku 4.5 | $0.00018 | $0.00219 |
Grade A, and why
trellis-plan-review 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 6d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review the Trellis planning artifacts at $ARGUMENTS. Persist the report. Leave planning artifacts and product code unchanged.
Commands below write
<skill-dir>as a placeholder. Substitute the literal skill directory path announced when this skill loads. Usepy -3wherepythonis not on PATH.
Hard gates
- Do not edit
prd.md,design.md,implement.md,*.jsonl,task.json, or product code. - Do not fix a defect you find. Do not produce a revised plan.
- The only allowed durable write is one review report under the reviewed project's
.trellis/reviews/directory, or a temporary--inputfile for the helper.Writeis not a grant to edit planning artifacts. - One selected review scope produces exactly one combined report and one handoff Prompt. Never create a report or Prompt per child. Do not delete, overwrite, or migrate historical child reports.
- Do not run
task.py start,task.py finish, or any Trellis command that writes state. - Every finding carries evidence. Drop any candidate you cannot cite.
Output mode
Detect the language of the request and surrounding discussion. Write the report in that language. Keep file paths, identifiers, commands, and code excerpts exact.
1. Locate the root task
The task directory may sit in another repository. Resolve it in this order:
- An explicit path in
$ARGUMENTS. python ./.trellis/scripts/task.py currentin the working repository.find . -maxdepth 5 -type d -name "<slug>"when only a slug is known, then widen the search root.
Read the root task.json first. Details: references/trellis-artifact-map.md.
2. Resolve one review scope
The root task and the recursive closure of task.json.children form one scope. Resolve children
root-first, preserving each children list's order. Search exact basenames in live tasks and
archive/*/; subtasks is a legacy fallback only when the children key is absent. A leaf is a
one-member scope.
Fail closed before judgment or report writing on a missing or ambiguous child, malformed metadata,
cycle, duplicate edge/member, unsafe path, or incorrect child parent backlink. Hierarchy expresses
ownership, not execution order. For every resolved member, read task.json and the existing planning
artifacts; each member's status decides whether Pass 7 applies.
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/interface.yaml 1.6 KB
- evals/evals.json 12 KB
- references/case-study-font-picker.md 7.3 KB
- references/claim-verification.md 4.1 KB
- references/finding-contract.md 7.3 KB
- references/handoff-prompt.md 11 KB
- references/report-template.md 1.8 KB
- references/review-passes.md 15 KB
- references/revision-question-gate.md 2.5 KB
- references/trellis-artifact-map.md 7.2 KB
- scripts/plan_precheck.py 28 KB runs code
- scripts/write_review_report.py 6.7 KB runs code
- tests/plan-precheck.test.mjs 16 KB runs code
- tests/tree-review-contract.test.mjs 5.2 KB runs code
- tests/write-review-report.test.mjs 15 KB runs code
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.
- 6d ago Changed · +3 lines f471711ec5f8
- 10d ago First seen · 164 lines · 184 tokens per session scan A b54bc80832a7
trellis-plan-review is a skill published in the GitHub repository bahayonghang/my-ai-cli-toolkit (16 stars, last pushed yesterday), licensed MIT. It adds 184 tokens to every session and 2,189 once invoked, about $0.0009 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
context-orchestrator
Build and maintain a reusable context pack for ongoing projects so every session starts with the same grounded context. Use when someone asks to "prepare context", "create session context", "summarize project state for agents", or wants deterministic handoff quality across multiple sessions and agents.
handoff
Use when managing a two-session handoff — inspecting, picking up, or reviewing a committed handoff package produced by a session=two scope run. The operator interface over the cross-environment handoff lifecycle (plan in one session, build in another, review back in the first). Trigger with /hyperflow:handoff, "list…
cocotrace
Build and query the SHA-256 requirements-to-implementation traceability graph across lifecycle artifacts.
cocoaudit
View and export the append-only session audit trail for regulated environments.
project-specification
Transforms project briefs into testable specifications with user stories and acceptance criteria. Use after brainstorming, before planning.
design-import
Scaffolds React components from a Claude Design handoff bundle and stops at files on disk: no stories, no tests, no pull request. Use when handed a claude.ai/design URL or a local bundle file; when that same scaffold should carry on through test generation, browser verification and an opened PR, run /ork:design-ship…