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/outlinedriven/odin-codex-plugin/to-issuesnpx skills add OutlineDriven/odin-codex-plugin --skill to-issuesgit clone --depth 1 https://github.com/OutlineDriven/odin-codex-pluginWrote 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/outlinedriven/odin-codex-plugin/to-issues)<a href="https://agentmods.dev/skills/outlinedriven/odin-codex-plugin/to-issues"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-codex-plugin/to-issues.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 | $0.00067 | $0.00782 |
| Opus 5 | $0.00034 | $0.00391 |
| Sonnet 5 | $0.00013 | $0.00156 |
| Haiku 4.5 | $0.00007 | $0.00078 |
Grade A, and why
to-issues 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- to-issues — 95% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Break a plan into tracer-bullet vertical slices. Each slice cuts end-to-end through every layer (schema, API, UI, tests) and is independently demoable. Reject horizontal layer-slices — they create blocked queues.
Emission Modes [LOCKED]
Default (file mode): Write to <project-root>/docs/issues/<feature>-slices.md as a numbered list of slices with the issue template per entry. Rerun-idempotent.
Flag mode (--emit-issue): After approval, create issues via gh issue create in dependency order so blocker references resolve to real numbers. Print URLs.
Process
1. Gather context
Read the source plan or PRD. If user passes a GitHub issue: gh issue view <number> --comments. If a plan file path: bat -P -p -n <path>. Otherwise work from active conversation.
2. Explore (if not already primed)
If the codebase is unfamiliar, dispatch an Explore agent. Trace integration layers: schema → service → API → UI → tests.
3. Draft vertical slices
Each slice MUST:
- Cut through every relevant layer
- Be demoable or verifiable on its own
- Be either AFK (no human needed) or HITL (decision/review required) — prefer AFK
- Be small enough that one engineer ships it in <2 days
Reject any slice that is "schema only" or "wire up later" — those are queue-blockers.
4. Quiz the user
Present the slate via a clarifying-question protocol. Show per slice: title, AFK/HITL, blocked-by references, user-stories covered. Ask: granularity correct? dependency edges correct? merge/split needed? AFK/HITL labels honest?
5. Emit
File mode: Write the approved slice list to docs/issues/<feature>-slices.md. Reference blockers by slice index. Commit.
Flag mode: gh issue create per slice in topological order. Capture each new issue number; backfill Blocked by with real numbers.
Issue Template
## Parent
#<parent-issue-number-or-PRD-path-or-omit>
## What to build
Concise end-to-end behavior description. Demoable outcome, not layer-by-layer mechanics.
## Acceptance criteria
- [ ] Observable criterion 1
- [ ] Observable criterion 2
## Blocked by
- #<issue-or-slice-number> (or "None — start immediately")
## User stories covered
- US-1, US-3
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 · 70 lines · 67 tokens per session scan A 85aff9754e35
to-issues is a skill published in the GitHub repository OutlineDriven/odin-codex-plugin (15 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 67 tokens to every session and 782 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 2026-08-30.
Other skills, from other repositories
triage-issue
Investigate a reported bug to root cause, then emit a TDD-shaped fix plan as an issue artifact. Trigger when the user reports a bug, says "triage", asks for issue investigation, or wants a fix plan before code changes.
git-guardrails-claude-code
Install a Claude-Code PreToolUse hook that blocks destructive git commands (push variants including force-push, hard reset, force clean, branch -D, checkout/restore overwrites) before Bash runs them. Use when the user wants git safety rails, force-push prevention, or repository-wipe protection.
duet
Two-party posture — user as director, agent as executor; every fork, tradeoff, or choice surfaced via batched AskUserQuestion with a recommended default. Use when the user invokes /duet, says "ask before" / "pair with me" / "human-in-the-loop", or for aesthetic/architectural/irreversible decisions.
explore
Read-only codebase exploration: discovery, structural reading, and emission of architecture/pattern/tooling/dependency summaries. Use to understand existing code, map files, trace function flow, locate symbols, or build pre-implementation context. Uses a staged 1/3/5 Explore-agent escalation protocol scaled to scope.…
deps-upgrade
Dependency-upgrade campaign — outdated scan, batch-by-severity, breaking-change remediation, lockfile audit. Use when CVEs require remediation, when a major upstream version lands, when stack compatibility forces a sweep, or on a scheduled (quarterly) hygiene cadence. CVE-driven bumps consume security audit findings…
design-by-contract
Design-by-Contract (DbC) development. Use when implementing with formal preconditions, postconditions, and invariants across any language.