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 cboone/agent-harness-plugins --skill create-deferred-issuesgit clone --depth 1 https://github.com/cboone/agent-harness-pluginsWrote 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/cboone/agent-harness-plugins/create-deferred-issues)<a href="https://agentmods.dev/skills/cboone/agent-harness-plugins/create-deferred-issues"><img src="https://agentmods.dev/badge/skills/cboone/agent-harness-plugins/create-deferred-issues/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/cboone/agent-harness-plugins/create-deferred-issues"><img src="https://agentmods.dev/badge/skills/cboone/agent-harness-plugins/create-deferred-issues.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 | $0.00045 | $0.07983 |
| Opus 5.5 | $0.00018 | $0.03193 |
| Sonnet 5.5 | $0.00009 | $0.01597 |
| Haiku 4.5 | $0.00005 | $0.00798 |
Grade A, and why
create-deferred-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 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 — 395 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Deferred Issues
Collect the concerns a unit of work set aside, propose them as one batch, and file the ones the user approves.
Why This Skill Exists
While working, an agent regularly names a concern and sets it aside: a formatter no CI job runs, a timeout far above real run lengths, a bug that belongs to another repository. Each one then waits for the user to say "file that", one round trip per concern, usually attached to the request to open the pull request. This skill gathers them in one pass and files the approved set in another.
Two rules shape everything below:
- The proposal is never skipped. Filing without confirmation would turn every hedge in the session into an issue, which is worse than filing nothing.
- Under-propose. A missed deferral costs the user one manual
/use-git:create-issue. A wrong one costs triage, and erodes trust in every later batch.
Options
The user may provide these options inline:
- --dry-run: Collect and propose, then stop. File nothing and post nothing.
- --no-comment: File the approved issues, but skip the summary comment on the source pull request or issue.
Parent Continuation Contract
When another skill invokes create-deferred-issues, that parent skill may provide an explicit continuation block immediately after the command:
Parent continuation:
- Caller: <parent skill name>
- Resume target: <parent workflow step to resume>
- On completion: <what the parent does next when issues were filed, none were found, none were fileable, none were approved, or this was a dry run>
- On filing failure: <what the parent does next when any approved issue failed to file>
Honor this block as part of the invocation, with one exception: the proposal in step 4 still stops for the user. A continuation block governs what happens after the user answers, never whether they are asked.
Final output for a parent invocation must include:
Deferred issues: <filed|none found|none fileable|none approved|dry run|failure>
Filed: <none|full issue URL, title, destination visibility; ...>
Already tracked: <none|concern and tracking reference; ...>
Cannot file: <none|concern and reason; ...>
Summary comment: <none|URL>
Caller resume target: <target from continuation block>
What ships with it
2 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.
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 Changed 78a24ee71693
- 8d ago Changed · +1 lines · +13 tokens per session a8ff57e16b61
- 15d ago Changed · +1 lines · -7 tokens per session 4a639931764a
- 26d ago Changed · -8 lines · -119 tokens per session 811e8d59ce89
- 29d ago First seen · 401 lines · 158 tokens per session scan A 75ea5894a19c
create-deferred-issues is a skill published in the GitHub repository cboone/agent-harness-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 7,983 once invoked, about $0.0002 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 2026-09-17.
Other skills, from other repositories
autopilot
Carry a well-scoped GitHub issue through the full dev loop autonomously, stopping at a per-run tier boundary (PR-ready, or merge+deploy for small reversible changes).
autopilot-triage
Vet open issues for autonomous resolution and queue the qualifying ones with the autopilot-queued label — the start-of-day "fill the queue" half of the triage → run split.
create-pr
Create a pull request with auto-generated description, issue linking, ROADMAP updates, and PR-metadata validation.
github-issue-lifecycle
A GitHub Issue workflow for taking a code change from request to review, approval, testing, and closure. It can also keep a GitHub Project board—the task board attached to a repository—in sync.
ensemblr
How Ensemblr works from inside it — the workspace/git-worktree model, the ensemblr control tools and what their answers mean, the committed .ensemblr/settings.toml (setup and run scripts, [git], [prompts], [infisical], environment variables), /.config/ensemblr/config.json, the Changes panel and diff comments, the…
lane-status
Is there anything for me to do on this project? Answers from the register's own state — your row, the other developer's row, what is unclaimed and runnable, what is held and why, which open questions hold a row, and who committed what this week. Triggers: anything for me to do, what should I work on, what should I do…