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/luanmorenommaciel/agentspec/github-post-issuenpx skills add luanmorenommaciel/agentspec --skill github-post-issuegit clone --depth 1 https://github.com/luanmorenommaciel/agentspecWhat 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 | $0.00181 | $0.02652 |
| Opus 5 | $0.00090 | $0.01326 |
| Sonnet 5 | $0.00036 | $0.00530 |
| Haiku 4.5 | $0.00018 | $0.00265 |
Grade A, and why
github-post-issue 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 yesterday.
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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Post Issue
Publish a drafted issue or ADR to GitHub via gh, with guardrails, and curate the board safely — one responsibility: hygienic mutation of the issue board. Authoring happens upstream (github-cr-issue / github-cr-adr); this skill is the gh write with checks around it, so nothing malformed, duplicated, or context-leaking reaches the public board. The recommended label taxonomy and its design rationale live in references/label-scheme.md.
When to use / Skip if
Use when:
- A drafted issue or ADR is ready to publish — typically a file under
.claude/sdd/drafts/. - The user asks to apply labels, set a parent/sub-issue relationship, or assign an owner.
- The board needs curation: closing duplicates or superseded issues, re-triaging labels.
Skip if:
- The content still needs drafting or restructuring — use
github-cr-issue/github-cr-adrfirst, then come back here. - The request is read-only (
gh issue list,gh issue view) — reads need no guardrails. - The work is a pull request, not an issue — use the PR workflow instead.
Step 0 — detect the repo (never hardcode)
Resolve the target dynamically so the skill works in whatever repository it is installed in:
REPO=$(gh repo view --json nameWithOwner -q .nameWithOwner) # preferred
[ -z "$REPO" ] && REPO=$(git remote get-url origin | sed -E 's#(git@|https://)github.com[:/]##; s#\.git$##') # fallback — normalize the remote URL to owner/repo
Pass --repo "$REPO" on every gh command below. A hardcoded repo writes to the wrong board the day this skill runs in a different checkout.
Before anything else, run gh auth status — this skill writes to the repository, and an authentication failure discovered at gh issue create, after the pre-flight gate has passed, strands the publish halfway. If it fails, stop and tell the user what to fix (gh auth login, or a token with repo scope).
Input
Accept either form:
- A draft file — typically
.claude/sdd/drafts/<type>-<slug>.md, produced bygithub-cr-issueorgithub-cr-adr. Preferred, because the draft is reviewable and diffable before it goes public. - In-conversation content the user asks to publish. Write it to a draft file first so the same flow (and
--body-file) applies.
What ships with it
1 file 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.
- yesterday First seen · 169 lines · 181 tokens per session scan A 5d94debad4a0
github-post-issue is a skill published in the GitHub repository luanmorenommaciel/agentspec (244 stars, last pushed 2d ago), licensed MIT. It adds 181 tokens to every session and 2,652 once invoked, about $0.0009 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 2026-09-01.
Other skills, from other repositories
babysit
Same-session monitoring loop for PRs, CI runs, tickets, and deployments using the monitorstart / monitorupdate / autonudgestop MCP tools. The loop re-injects your check instructions into THIS session on an idle interval — same context, same tools — and works from dashboard chat, Slack threads, and Discord DMs. Use…
agile-product-owner
../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.
teamharness-task-delegation
Use when a Leader turns ready Quick Task or Project Work state into Worker task instructions, sends assignment messages, checks submitted results, and defines completion/blocker report contracts. Do not use to create projects, create rooms, or execute Worker tasks.
gsd-executor
Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.
dot-ai-prd-create
Create documentation-first PRDs that guide development through user-facing content.
agent-upkeep
Perform one small, scoped maintenance improvement to the Elements monorepo and open a single reviewable pull request. Use this skill for scheduled or unattended upkeep runs that improve unit test coverage for one file, fix one behavioral bug in one module, or move one off ESLint rule toward enforcement to reduce…