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 kreek/consult --skill issue-trackinggit clone --depth 1 https://github.com/kreek/consultWrote 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/kreek/consult/issue-tracking)<a href="https://agentmods.dev/skills/kreek/consult/issue-tracking"><img src="https://agentmods.dev/badge/skills/kreek/consult/issue-tracking/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/kreek/consult/issue-tracking"><img src="https://agentmods.dev/badge/skills/kreek/consult/issue-tracking.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 | $0.00022 | $0.01108 |
| Opus 5.5 | $0.00009 | $0.00443 |
| Sonnet 5.5 | $0.00004 | $0.00222 |
| Haiku 4.5 | $0.00002 | $0.00111 |
Grade A, and why
issue-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 14d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue Tracking
Iron Law
INITIATIVE > EPIC > ISSUE. EVERY ISSUE FITS IN ONE SPRINT AND CLOSES ON EVIDENCE.
When to Use
- The user asks to draft, split, update, or close a ticket, issue, epic, or initiative in any tracker.
- The user wants an agreed design turned into tracked work, or tracker status.
- The task cites a tracker item, such as "fix #123" or "PROJ-42".
When NOT to Use
- Deciding what to build. Use
specifyfirst. - Planning one change's steps. Use the
workflowRule 9 plan file.
Rules
- Three levels, at most one parent each. An Initiative groups Epics toward one measured outcome. An Epic groups Issues that deliver one feature. Nothing goes below an Issue. A bug or chore that serves no feature stands alone. Never create a placeholder parent or a catch-all Epic.
- Map the levels onto what the tracker already has. Read its templates,
types, and hierarchy, use its level names, and search for duplicates and
the right parent. Prefer native types and parent links to labels or title
prefixes. New types, labels, fields, or hierarchy levels are durable shapes
under
workflowRule 7. - Size by the team's sprint, not the agent's speed. Read the sprint length from the tracker, or assume two weeks and say so. An Issue fits when one engineer can finish it, review included, within half a sprint, with at most five acceptance criteria. Otherwise split it, or file a time-boxed research Issue that ends in a decision. An Epic with one Issue is an Issue. An Epic longer than a quarter is two Epics or an Initiative.
- Split by behavior, not by layer or activity. A feature Issue changes one behavior a user, caller, or operator can observe. A refactor or chore Issue names the behavior it preserves and the check that proves it.
- Keep Issues short, and state outcomes, not implementation. An Issue
body stays under 200 words, excluding code and logs, because developers
skim longer ones. Link the Epic or Initiative instead of repeating its
context. Criteria name observable results, not "tests written". Leave out
steps and pseudocode. A criterion that fixes a caller-facing shape stays
proposed until
contract-firstapproves it. When a criterion proves wrong mid-build, propose an edit instead of rewriting it. - The team owns estimates, priority, sprint, assignee, and dates. Leave them empty unless the user or tracker supplies them. Where another skill wants an owner or date, ask or write TBD. Leave items you were not asked to change untouched.
- Write to the tracker only when the user asks for tracker work. An Issue
named in a task authorizes only reading it and citing it in branch, commit,
and PR text.
git-workflowRule 3 covers each item's text. Get the whole tree approved: each item's level, title, parent, and body. After a partial failure, report what exists and search before retrying. With no human to answer, write drafts todocs/plans/<slug>-issues.mdand publish nothing. - Keep private data out of tracker text. Redact secrets, personal data, and internal hosts from logs. Report vulnerabilities through the project's private channel, never a public item.
- Done means evidence, not closed children. A PR or commit closes an Issue only when it meets every acceptance criterion. Otherwise it references the Issue. Out-of-scope work becomes a drafted follow-up. An Epic closes when each exit criterion has evidence. An Initiative closes when its measure is met or its owner cancels it.
- Status reports link the tracker. Report only finished work, blockers and causes, risks, scope changes, decisions needed, and Initiative measures.
What ships with it
5 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.
- 14d ago First seen · 92 lines · 22 tokens per session scan A 64a4eb692b8e
issue-tracking is a skill published in the GitHub repository kreek/consult (1 stars, last pushed 14d ago), licensed MIT. It adds 22 tokens to every session and 1,108 once invoked, about $0.0001 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 2026-10-02.
Other skills, from other repositories
catchup
Summarize and review what changed while you were away. Use after a weekend, vacation, or flight to check missed PRs, git commits, Linear tickets, and meetings — one prioritized brief, not a firehose.
phx-deps-update
Bump outdated Hex deps — inventory, snapshot changelogs, update, fix breaks, split reviewable PRs (patches bundled, majors solo). Use to upgrade/bump Elixir dependencies or when versions fall behind. NOT for deps.get failures (phx-investigate).
customer-success-management
Runs the ongoing relationship with accounts after the sale — segmenting coverage against account value, building a health score that predicts rather than describes, running reviews customers find worth attending, forecasting renewals honestly, and finding expansion that follows usage instead of quota. Use this to…
service-desk
Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets…
incident-management
Runs an operational incident from detection to closed action — declaring it and naming a commander, separating the people restoring service from the people communicating, keeping a timeline as it happens, deciding when it is over, and running a review that produces a small number of changes someone actually completes.…
estimating-and-contingency
Produces a cost or effort estimate someone can defend — decomposing the work, choosing between analogous, parametric and bottom-up methods, documenting the basis and its assumptions, expressing confidence as a range, and sizing contingency and management reserve separately. Use this to build an estimate, challenge one…