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/noahrasheta/director/resumenpx skills add noahrasheta/director --skill resumegit clone --depth 1 https://github.com/noahrasheta/directorWrote 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/noahrasheta/director/resume)<a href="https://agentmods.dev/skills/noahrasheta/director/resume"><img src="https://agentmods.dev/badge/skills/noahrasheta/director/resume.svg" alt="Measured on agentmods" 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 | $0.00020 | $0.02771 |
| Opus 5 | $0.00010 | $0.01385 |
| Sonnet 5 | $0.00004 | $0.00554 |
| Haiku 4.5 | $0.00002 | $0.00277 |
Grade A, and why
director:resume 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 4d 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Director's resume command. Help the user pick up where they left off by summarizing what happened last time, detecting what changed while they were away, and suggesting what to do next.
Read these references for tone and terminology:
reference/plain-language-guide.md-- how to communicate with the userreference/terminology.md-- words to use and avoid
Follow all 7 steps below IN ORDER. Stop at Step 1 if no project exists. Otherwise, continue through the full resume flow and present a single cohesive message at the end.
Dynamic Context
<project_state>
!cat .director/STATE.md 2>/dev/null || echo "NO_PROJECT"
</project_state>
<project_config>
!cat .director/config.json 2>/dev/null || echo "{}"
</project_config>
<recent_git>
!git log --oneline -20 2>/dev/null || echo "NO_GIT"
</recent_git>
<external_changes>
!git diff --stat 2>/dev/null || echo "NO_CHANGES"
</external_changes>
Step 1: Check for a project
Look at the injected <project_state> above.
If it contains "NO_PROJECT" (no .director/ folder exists), say:
"No project to resume. Want to get started with /director:onboard? I'll ask a few questions about what you're building."
Stop here if no project.
Step 1b: Handle inline context
If $ARGUMENTS is non-empty, store it as focus context for use in Steps 3 and 6.
The inline text influences the resume experience:
- In Step 3 (reconstruct last session): when summarizing what was accomplished, highlight any work related to the user's focus text.
- In Step 6 (suggest next action): when suggesting the next task, if there is a pending task matching the focus text, suggest that task specifically. If no match, acknowledge the focus: "You mentioned [arguments] -- the next ready task is [task name], which [explain how it relates or doesn't]."
Examples:
/director:resume "authentication"-- highlights auth-related work in the recap and suggests auth-related next tasks/director:resume "let's finish the dashboard"-- focuses the next-action suggestion on dashboard tasks
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.
- 4d ago First seen · 237 lines · 20 tokens per session scan A 6f61397e9125
director:resume is a skill published in the GitHub repository noahrasheta/director (1 stars, last pushed 6mo ago), licensed MIT. It adds 20 tokens to every session and 2,771 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
gsd-graphify
Build, query, and inspect the project knowledge graph in .planning/graphs/.
gsd-mempalace-capture
File a phase artifact into MemPalace; mirror decision facts into its temporal KG.
gsd-mempalace-recall
Recall decisions, patterns, and surprises from MemPalace before planning.
gsd-thread
Manage persistent context threads for cross-session work.
handoff
Prepare a clean cross-session handoff so the next agent can pick up where you left off. Writes a focused continue.md in the active slice dir and ensures STATE.md + summary artifacts are current. Use when asked to "hand off", "prepare handoff", "pause work", "bookmark this", "I'll come back to this later", before…
gsd-quick
Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents.