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-apply-goal)<a href="https://agentmods.dev/skills/hmj1026/dhpk/dhpk-opsx-apply-goal"><img src="https://agentmods.dev/badge/skills/hmj1026/dhpk/dhpk-opsx-apply-goal/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-apply-goal"><img src="https://agentmods.dev/badge/skills/hmj1026/dhpk/dhpk-opsx-apply-goal.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 | $0.00070 | $0.03844 |
| Opus 5 | $0.00035 | $0.01922 |
| Sonnet 5 | $0.00014 | $0.00769 |
| Haiku 4.5 | $0.00007 | $0.00384 |
Grade A, and why
dhpk-opsx-apply-goal 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 today.
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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
opsx-apply-goal
This skill has one job: turn an existing OpenSpec change into a bounded
/goal <condition> command. It reads the change artifacts, folds the
Skill-tool openspec-apply-change kickoff into the condition, and emits one
command for a fresh session to run the change unattended.
Why single-paste: Claude Code's
/goaltriggers immediate action as soon as it is submitted — there is no window to paste a follow-up/opsx:applycommand afterward. So the kickoff instruction ("invoke the Skill tool with the canonical IDopenspec-apply-change") is embedded as the first sentence of the/goalcondition itself, and the whole thing is delivered as one paste. Do not split this back into a/goalstep followed by a separate/opsx:applystep — that leaves no input window for the second command.Review Gate strategy: the goal records one identity-bound Review Gate obligation check after implementation. It accepts only a durable resolved verdict for every applicable reviewer obligation (or
NOT_APPLICABLE), not a message or a file-presence claim. Seereferences/detection.mdfor the obligation rationale and detection-flag table.
References
| File | Read when |
|---|---|
scripts/analyze-change.sh |
Step 1 — deterministic argument normalization, change-dir location, checkbox counts, and turn budget |
scripts/goal-context.js |
Step 1 — helper I/O for fast-worker selection, E2E detection, and the task digest |
references/detection.md |
Step 2 — test/build/lint/coverage/smoke signal tables, non-automatable-task signals, and Review Gate rationale |
references/gate-contracts.md |
Step 3 — compact evidence contracts that every emitted gate must preserve |
references/goal-templates.md |
Steps 3–4 — verbatim Part 0–4 /goal condition templates, including the single full variant |
references/output-blocks.md |
Output — complete Block A/B/C/C2 contract, hard-stop branch, and session handoff |
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.
- today Changed · +8 lines e618ae684448
- 6d ago First seen · 222 lines · 70 tokens per session scan A bd7eabcf85bc
dhpk-opsx-apply-goal is a skill published in the GitHub repository hmj1026/dhpk (2 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 3,844 once invoked, about $0.0003 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
harness
A meta-skill for designing and maintaining a project harness: a coordinated set of specialist agents, skills, and project instructions. It defines their roles, connects them to the project, and updates the setup as the work changes.
plumb-line-audit
Use when auditing a diff or repository against the plumb-line principles — finds laundered uncertainty, boundary leaks, hardcoded priors, overstated maturity, outputs lacking recorded lineage, and baseline drift with no explanation. Read-only: it reports, never auto-fixes.
plumb-line-bootstrap
Use when setting up a project with the plumb-line discipline — interviews the builder to find their source-truth layer and layering, generates a domain-neutral ruleset, and installs parameterized enforcement (boundary check, test gate, pre-commit gate, branch guard) for the project's language. Ships no default layers…
ship
A final delivery check for a project or product release. It verifies that planned features are complete, the build and tests pass, and a validation sample reaches the required result.
dev-plan
A planning tool that breaks a software project into features arranged in dependency-based waves, or groups of work that can be done in sequence or parallel.
research
A research workflow that assigns separate agents to study open-source projects, competing products, and current development practices. Git worktrees are separate working copies used to keep those investigations isolated.