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.
git clone --depth 1 https://github.com/juliusz-cwiakalski/agentic-delivery-osWrote 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/commands/juliusz-cwiakalski/agentic-delivery-os/plan-change)<a href="https://agentmods.dev/commands/juliusz-cwiakalski/agentic-delivery-os/plan-change"><img src="https://agentmods.dev/badge/commands/juliusz-cwiakalski/agentic-delivery-os/plan-change/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/commands/juliusz-cwiakalski/agentic-delivery-os/plan-change"><img src="https://agentmods.dev/badge/commands/juliusz-cwiakalski/agentic-delivery-os/plan-change.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 | $0.00013 | $0.02715 |
| Opus 5 | $0.00006 | $0.01358 |
| Sonnet 5 | $0.00003 | $0.00543 |
| Haiku 4.5 | $0.00001 | $0.00271 |
Grade A, and why
plan-change 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 2d 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 — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This command:
- Discovers or confirms the workItemRef (e.g.,
PDEV-123,GH-456) by scanning existing change specs or querying the tracker. - Orients itself in the repository and high-level documentation under
doc/spec/and related docs. - Systematically elicits and refines all information needed by
/write-spec(WHY, outcomes, boundaries, contracts, risks, NFRs, etc.). - Concludes with a compact
<change_planning_summary>plus a clear recommendation to invoke/write-spec <workItemRef>.
This command never writes files or modifies Git state; it operates purely via conversational planning and read-only repository inspection.
<workItemRef_resolution> Primary goal: determine the canonical workItemRef for this planning session.
Resolution rules:
-
If workItemRefHint is provided:
- Validate format: uppercase prefix + hyphen + digits (e.g.,
PDEV-123,GH-456). - Treat as proposed workItemRef; ask user to confirm or override.
- Validate format: uppercase prefix + hyphen + digits (e.g.,
-
If no workItemRefHint:
- Discover existing specs by scanning:
doc/changes/**/chg-*-spec.md. - For each match, parse the workItemRef segment (e.g.,
chg-PDEV-123-spec.md→PDEV-123). - Propose creating a new ticket via
@pmor ask user to provide an existing reference. - If user provides a new reference, validate format and confirm.
- Discover existing specs by scanning:
-
Once confirmed, use workItemRef consistently in all summaries and handoff commands.
This command MUST NOT create folders or files in doc/changes/; it only proposes and confirms the identifier for downstream commands.
</workItemRef_resolution>
<context_sources> The planning agent may read from the repository to ground questions, but must not modify files.
Primary sources:
doc/spec/**: system-level and feature-level specifications.doc/overview/**: domain and product overview documents.doc/decisions/**: architecture decision records.doc/domain/**,doc/diagrams/**: architecture, flows, constraints.- Existing change specs under
doc/changes/**/chg-*-spec.mdfor related changes.
Usage rules:
- When user describes the change, infer domain keywords and search documentation.
- Summarize only relevant parts in concise bullets; do not paste large documents.
- Quote document titles and short excerpts; ask user to confirm context anchors.
- Treat existing specs and ADRs as authoritative constraints unless explicitly revisiting. </context_sources>
<session_flow>
-
Initialization & orientation
- Confirm single repository scope and target service/app.
- Resolve and confirm workItemRef using workItemRef_resolution.
- Ask for short, plain-language description of the desired change.
- If ideaSeed provided, restate for confirmation.
-
Clarify problem and context
- Elicit: current state, pain points, affected users, triggers, constraints.
- Probe for singular, measurable problem statement.
- Identify change type: feat|fix|refactor|docs|test|chore|perf|build|ci|revert|style.
-
Define goals and success metrics
- Separate: business goals, user goals, operational goals.
- For each goal, elicit measurable success metric (baseline, target, window).
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.
- 2d ago First seen · 311 lines · 13 tokens per session scan A 3929c0080b10
plan-change is a command published in the GitHub repository juliusz-cwiakalski/agentic-delivery-os (37 stars, last pushed 2d ago), licensed MIT. It adds 13 tokens to every session and 2,715 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-07.
Other commands, from other repositories
deps-audit
Audit project dependencies for vulnerabilities, outdated packages, license conflicts, and supply chain risks — then provide actionable remediation strategies.
README
Git workflow and quality assurance commands for the claude-skills repository.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
growth-seo
SEO audit and optimization for organic search ranking.
growth-ab-test
Command "growth-ab-test" from christopherlouet/claude-base, covering growth-ab-test agent, context, objective, workflow and expected output.