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/yonatangross/orchestkit/issue-progress-trackingnpx skills add yonatangross/orchestkit --skill issue-progress-trackinggit clone --depth 1 https://github.com/yonatangross/orchestkitWrote 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/yonatangross/orchestkit/issue-progress-tracking)<a href="https://agentmods.dev/skills/yonatangross/orchestkit/issue-progress-tracking"><img src="https://agentmods.dev/badge/skills/yonatangross/orchestkit/issue-progress-tracking.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 | $0.00073 | $0.01118 |
| Opus 5 | $0.00036 | $0.00559 |
| Sonnet 5 | $0.00015 | $0.00224 |
| Haiku 4.5 | $0.00007 | $0.00112 |
Grade A, and why
issue-progress-tracking 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue Progress Tracking
Ceremony guide for tracking GitHub issue progress via gh CLI. Ensures issues stay updated as work progresses from start to PR.
Invocation
This skill is user-invocable: false and disable-model-invocation: true:
there is no /ork: form and the model cannot auto-select it (#3313). An agent
loads it explicitly by Reading this file's path:
${CLAUDE_PLUGIN_ROOT}/skills/issue-progress-tracking/SKILL.md
Phase 1: Start Work
Label the issue and create a feature branch:
# Move issue to in-progress
gh issue edit $ARGUMENTS[0] --add-label "status:in-progress" --remove-label "status:todo"
gh issue comment $ARGUMENTS[0] --body "Starting work on this issue."
# Create feature branch
git checkout -b issue/$ARGUMENTS[0]-brief-description
Rules:
- Always branch from the default branch (main/dev)
- Branch name format:
issue/<number>-<brief-description> - Never work directly on main/dev
Phase 2: During Work — Small Commits
Commit after each logical step, not at the end. Every commit references the issue:
# Each commit references the issue number
git commit -m "feat(#$ARGUMENTS[0]): add user model
Co-Authored-By: Claude <[email protected]>"
Rules:
- One logical change per commit (atomic)
- Reference issue in every commit:
type(#N): description - Commit early and often — don't accumulate a massive diff
Phase 3: Report Progress (Long Implementations)
For multi-step work, post progress updates:
gh issue comment $ARGUMENTS[0] --body "Progress update:
- Completed: database schema, API endpoints
- In progress: frontend components
- Remaining: tests, documentation"
When to post updates:
- After completing a major milestone
- When blocked or changing approach
- Before stepping away from a long task
Phase 4: Complete Work
Create the PR and update labels:
# Create PR that closes the issue
gh pr create \
--title "feat(#$ARGUMENTS[0]): brief description" \
--body "Closes #$ARGUMENTS[0]
## Changes
- Change 1
- Change 2
## Test Plan
- [ ] Unit tests pass
- [ ] Manual verification"
# Update issue status
gh issue edit $ARGUMENTS[0] --add-label "status:in-review" --remove-label "status:in-progress"
What ships with it
4 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.
- yesterday First seen · 155 lines · 73 tokens per session scan A a3955bc34cae
issue-progress-tracking is a skill published in the GitHub repository yonatangross/orchestkit (225 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 1,118 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
hive-workflow
Issue tracking and task management using the hive system. Use when creating, updating, or managing work items. Use when you need to track bugs, features, tasks, or epics. Do NOT use for simple one-off questions or explorations.
quick
Execute an ad-hoc task with atomic commits. Skips full plan/review.
github-manager
GitHub operations - manage issues, pull requests, repositories, and workflows via GitHub API.
codeflow-maintainer
OpenClaw-only maintainer PR workflow modes and skills. For OpenCoven/coven PR creation, redirect to skills/pr-agent, the Coven PR Readiness Agent.
gitlab-issues
Issue review and tracking on GitLab via the gitlab-api MCP server — review a project's issues, review issues across a whole group/organization, and read, create, update, or close an issue with the domain-typed tool. Use when the agent must triage a project's issues, see every issue affecting a group, open a new issue…
issue-comment
Handle a non-build maintainer comment on an issue or PR — close, reopen, label, dedupe, answer a brief question, or triage. Action-only; redirect anything that needs code changes to /build.