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 hmj1026/dhpk --skill opsx-apply-resumegit clone --depth 1 https://github.com/hmj1026/dhpkWrote 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/hmj1026/dhpk/opsx-apply-resume)<a href="https://agentmods.dev/skills/hmj1026/dhpk/opsx-apply-resume"><img src="https://agentmods.dev/badge/skills/hmj1026/dhpk/opsx-apply-resume/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/hmj1026/dhpk/opsx-apply-resume"><img src="https://agentmods.dev/badge/skills/hmj1026/dhpk/opsx-apply-resume.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 | $0.00072 | $0.01222 |
| Opus 5.5 | $0.00029 | $0.00489 |
| Sonnet 5.5 | $0.00014 | $0.00244 |
| Haiku 4.5 | $0.00007 | $0.00122 |
Grade A, and why
opsx-apply-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 yesterday.
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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenSpec Apply Resume
$opsx-apply-resume is the explicit handoff capability behind
/dhpk:opsx-apply-resume. It snapshots enough live state to cross a context
boundary and restores it later; the live worktree remains the source of truth.
$SKILL_DIR denotes the physical directory containing the selected SKILL.md;
it is path notation, not an ambient environment variable or repository-root
lookup. Resolve it once before invoking a package-local helper and keep the
consumer's current working directory unchanged.
When to Use
- An explicit invocation requests Save while a long-running apply session is approaching its context limit.
- An explicit invocation requests Resume after a context/session boundary.
- A previous handoff is in
savedorconsumingstate and needs recovery.
When NOT to Use
- Creating, designing, verifying, or archiving an OpenSpec change.
- Replacing the external
openspec-apply-changeSkill or modifying its files. - Reverting, deleting, or stashing uncommitted work to make a handoff look clean.
Host and package resolution
- Detect the current Host from the native runtime; do not add a public host
flag. Claude uses
.claude/artifacts/apply-resume/latest.md; Codex uses.dhpk/artifacts/apply-resume/latest.md. - Resolve the handoff path once and pass it explicitly to every package-local
helper and context loader. Resolve helper executors from
"$SKILL_DIR/scripts/"; helpers must never rediscover a path from their current directory or a parent/peer Skill. A missing helper/reference isBLOCKED_RESOURCE_MISSING. - Load only Save or Resume after phase detection. Keep optional providers undisclosed until their branch is selected.
Workflow
- Interpret the requested task: saving current apply progress selects Save;
restoring saved progress selects Resume. Optional
saveandresumewords express the same tasks. With only a change ID, detect the phase. Parse an optionalchange-id; priority is argument, latest visible apply invocation, then the Host's native selection prompt. If no change can be selected, stopBLOCKED. - Run the package-local phase detector with the explicit handoff path. Honor
the requested phase after checking existing state: a recent save is a
confirmation boundary;
consumingis a recovery boundary. - Follow exactly one phase reference. Save writes a new
latest.md; Resume loads it, validates the change, and archives it only after successful continuation. - Keep optional commit, precommit, compact, and memory providers visibly optional. Their absence or failure never erases live files or invalidates a handoff summary.
- Hand successful continuation to the available canonical
openspec-apply-changeSkill. Claude may use native Skill dispatch; Codex invokes the available projected skill directly. If it is unavailable, reportUNAVAILABLEand keep the handoff recoverable; never edit the external skill or substitute/opsx:applyas a Skill ID.
What ships with it
13 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/openai.yaml 245 B
- distribution.yaml 3.9 KB
- evals/evals.json 6.1 KB
- references/load-context.md 4.3 KB
- references/post-observation.md 3.1 KB
- references/resume.md 4.9 KB
- references/save.md 6.4 KB
- scripts/detect-phase.sh 2.8 KB runs code
- scripts/extract-compact.sh 1.6 KB runs code
- scripts/lib/portable-sed.sh 534 B runs code
- scripts/post-obs.sh 5.8 KB runs code
- scripts/set-handoff-state.sh 2.4 KB runs code
- scripts/write-handoff.sh 6.5 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.
- yesterday Changed · +12 lines 48c1ba758b2c
- 23d ago First seen · 107 lines · 72 tokens per session scan A 0e27e88ab005
opsx-apply-resume is a skill published in the GitHub repository hmj1026/dhpk (2 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 1,222 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 2026-09-24.
Other skills, from other repositories
promote-idea
Converts an album idea from IDEAS.md into an actual album project in one step. Use when the user says "promote [idea title]", "turn idea into album", or "start working on [idea]".
customer-onboarding-and-implementation
Takes a new customer from signature to working — setting a definition of live that both sides agreed before the contract was signed, planning and staffing the implementation, running data migration and integration realistically, training the people who will actually use it, and handing over to the ongoing…
recap-doc
Post-development recap document generator. Use when: AI/Codex has implemented a feature and the user needs a guided walkthrough of what changed and why, with blind-spot detection and anticipated questions. Not for: Q&A follow-up (use /recap-ask), technical share-out for teammates (use /tech-brief), or generic code…
runbook
Generate and update feature release runbooks from existing docs and codebase. Use when: creating operational runbook, release handbook, deployment checklist, pre-release preparation. Not for: incident response (v2), code review (use codex-code-review), architecture design (use architecture).
show-me-your-work
For autonomous multi-phase or unattended work, a reviewer needing an evidence trail, or an explicit decision-log/show-your-work request, keep an append-only decision log with why, evidence, and result. Record decisions and corrections, not hidden reasoning transcripts.
ccc-onboard
Contributor first-hour plan for the current repository: reads CLAUDE.md, BIBLE.md and package.json, checks required tools, asks the contributor's role, and returns a five-step checklist plus five real starter resources. Use when someone new joins a repo or types $ccc-onboard.