Borrowing it
Nothing to install: this file belongs to PackmindHub/packmind. 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/PackmindHub/packmind/main/.claude/skills/agentic-design-session/SKILL.mdgit clone --depth 1 https://github.com/PackmindHub/packmindWrote 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/packmindhub/packmind/agentic-design-session)<a href="https://agentmods.dev/skills/packmindhub/packmind/agentic-design-session"><img src="https://agentmods.dev/badge/skills/packmindhub/packmind/agentic-design-session/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/packmindhub/packmind/agentic-design-session"><img src="https://agentmods.dev/badge/skills/packmindhub/packmind/agentic-design-session.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 | $0.00133 | $0.01559 |
| Opus 5.5 | $0.00053 | $0.00624 |
| Sonnet 5.5 | $0.00027 | $0.00312 |
| Haiku 4.5 | $0.00013 | $0.00156 |
Grade A, and why
agentic-design-session 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 1mo 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design session
You are settling how, and recording it so it survives. The main output is
.claude/features/<slug>/decisions.md, from
.claude/pipeline/decision-log.template.md. Read the charter first.
You also close by filling one section of the charter — Size and sessions — and
that is the only edit you may make outside the decision log. It is the last step
of this skill, described at the bottom.
Why the rejected alternatives matter more than the decisions
An orchestrator will re-encounter every fork you settle here when it writes specs, weeks of context later. Given only the decision, it does one of two things: re-opens the question, or contradicts it without noticing. Given the decision plus why the obvious alternative was rejected, it recognises the fork and moves on.
So a Rejected bullet with no reason is worth nothing. "We rejected polling" is
not a record; "we rejected polling because the p99 gap has to stay under a
second and the poll interval that allows would cost more than the socket" is.
The same applies when you turn out to be wrong. A superseded decision keeps its reasoning in the file, because the reason it looked right is exactly what stops someone re-proposing it in three weeks.
Hard rules
- Write no code. Types, signatures and schemas are decisions, and you may quote a signature in a decision. You may not implement one.
- Edit no file but the decision log, and the charter's
Size and sessionssection at the close. Nothing else in the charter is yours to touch — if framing got a criterion wrong, say so and let the user reopen phase 1a. - Append only. Never rewrite a decided entry. To change one, add a new entry
with
supersedes: D-00n, and appendsuperseded-by:to the old one. That one line is the only permitted mutation. - Never leave a fork implicit. If you notice yourself assuming something, that assumption is a decision, and it goes in the log.
How to run the conversation
Surface the assumptions first. Before proposing anything, say out loud what the charter appears to take for granted. Most bad designs are not chosen; they are inherited from an unexamined premise. Ask about each one.
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.
- 1mo ago First seen · 124 lines · 133 tokens per session scan A 8192aa58bff6
agentic-design-session is a skill published in the GitHub repository PackmindHub/packmind (319 stars, last pushed 4d ago), licensed Apache-2.0. It adds 133 tokens to every session and 1,559 once invoked, about $0.0005 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 2026-09-17.
Other skills, from other repositories
ce-compound
Document a recently solved problem or durable project vocabulary in docs/solutions/ or CONCEPTS.md. Use when capturing a learning after work.
ce-work
Execute a plan or concrete work prompt end-to-end. Use when implementing from docs/plans, a spec path, or a clear build request; use ce-debug for open-ended bugs.
sdd
Execute the Liatrio Spec-Driven Development (SDD) workflow when explicitly invoked by the user. NOTE: this skill is NOT intended to be dynamically loaded or automatically triggered; it should only ever be explicitly called by the user.
loadout-import-workflow
Import another repo's command/skill suite into loadout as a workflow. Use when the user points at an agent framework, plugin, or command pack (e.g. a GitHub repo, a .claude/commands/ directory, a skills pack) and wants its process turned into a loadout [[workflows]] entry — "import this workflow", "turn this plugin…
ce-commit-push-pr
Commit, push, and open a PR. Use when asked to ship/open a PR, or for PR-description-only flows like writing, rewriting, or describing a PR body.
loadout-migrate
Migrate existing global AI agent instructions into loadout. Use when adopting loadout, importing a CLAUDE.md / AGENTS.md / global agent rules into loadout, setting up /.config/loadout/config.toml, or turning prose agent instructions into reusable fragments and stack-targeted profiles.