Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add hmj1026/dhpk/plugin install 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/dhpk-opsx-load-context)<a href="https://agentmods.dev/skills/hmj1026/dhpk/dhpk-opsx-load-context"><img src="https://agentmods.dev/badge/skills/hmj1026/dhpk/dhpk-opsx-load-context/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/dhpk-opsx-load-context"><img src="https://agentmods.dev/badge/skills/hmj1026/dhpk/dhpk-opsx-load-context.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 | $0.00116 | $0.01763 |
| Opus 5 | $0.00058 | $0.00881 |
| Sonnet 5 | $0.00023 | $0.00353 |
| Haiku 4.5 | $0.00012 | $0.00176 |
Grade A, and why
dhpk-opsx-load-context 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 3d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
opsx-load-context
Context loading skill for opsx-apply-resume Resume Phase.
Implements a 3-tier fallback so that context is always available even if earlier tiers fail.
When NOT to Use
- Saving / posting a session observation → use
dhpk-opsx-post-observation - Generating a
/goalcondition for a fresh session → usedhpk-opsx-apply-goal - Any phase other than
opsx-apply-resumeResume Phase (Steps 1b–1d)
Inputs
| Variable | Source | Description |
|---|---|---|
claude_mem_obs_id |
Handoff frontmatter | Integer obs ID, or null / absent |
compact_json_path |
Handoff frontmatter | Relative path like compact-notes/compact-*.json, or absent |
next_action_hint |
First Next Action from handoff | Key terms for cross-session search; may be empty |
Fallback Chain
Work through tiers in order. Stop at the first successful tier and record CONTEXT_SOURCE.
Pre-chain — Hard-rule escalation (highest priority — blocking human decision)
Condition: An active change carries a .hard-rule-escalation.md written by
dhpk-opsx-apply-goal because unattended implementation hit an explicit hard-rule
conflict that could not be resolved without human input. Check this before
routine carry-forward such as .resume-note.md.
ESCALATION=$(ls -t openspec/changes/*/.hard-rule-escalation.md 2>/dev/null | head -1)
- File found → read it and surface it as a blocking human decision. Set
CONTEXT_SOURCE = ".hard-rule-escalation.md". Do not fold it into ordinarysession_goal/in_progressresume context, and do not continue the goal loop until the human explicitly decides how to resolve the rule conflict. - No file (the common case) → fall through to the unattended stop resume note.
Best-effort only: a malformed or unreadable escalation file still blocks; report the path and ask the human to inspect it.
Pre-chain — Unattended stop resume note (checked after hard-rule escalation)
Condition: An active change carries a .resume-note.md (written by
dhpk-opsx-apply-goal's Part 4 when an unattended session hit its turn or wall-clock
limit). Check this before the tiers below — it is the freshest, most specific
carry-forward for a resumed run.
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.
- 3d ago First seen · 164 lines · 116 tokens per session scan A 5bad96e9fd46
dhpk-opsx-load-context is a skill published in the GitHub repository hmj1026/dhpk (2 stars, last pushed today), licensed MIT. It adds 116 tokens to every session and 1,763 once invoked, about $0.0006 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 2026-09-05.
Other skills, from other repositories
handoff
A session-closing checklist for recording work and confirming that a project is ready to continue later.
event-review
A weekly review process for event logs and leftover task records, turning repeated problems or useful lessons into proposed memory, knowledge, or skill entries.
resume
A project-resumption workflow for picking up work after a break. It checks that the project’s safeguards are active, compares the current state with the previous session, and rebuilds the working context.
lessons
An error and lessons journal for a project. It shows recent mistakes, whether they were addressed, and lessons saved for future work.
last30Days
Resolve "last30Days" to a concrete ISO date range relative to your run time — a rolling 30-day window ending today. Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a "last 30 days" / trailing-month task…
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…