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 grandcamel/JIRA-Assistant-Skills --skill jira-assistantgit clone --depth 1 https://github.com/grandcamel/JIRA-Assistant-SkillsWrote 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/grandcamel/jira-assistant-skills/jira-assistant)<a href="https://agentmods.dev/skills/grandcamel/jira-assistant-skills/jira-assistant"><img src="https://agentmods.dev/badge/skills/grandcamel/jira-assistant-skills/jira-assistant/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/grandcamel/jira-assistant-skills/jira-assistant"><img src="https://agentmods.dev/badge/skills/grandcamel/jira-assistant-skills/jira-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 235 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- medium Excessive Agency · line 234 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00037 | $0.02442 |
| Opus 5 | $0.00018 | $0.01221 |
| Sonnet 5 | $0.00007 | $0.00488 |
| Haiku 4.5 | $0.00004 | $0.00244 |
Grade A, and why
jira-assistant 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 12d 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:
- jira-assistant — 91% identical, 26 lines differ
How it starts
The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
JIRA Assistant
This hub routes requests to specialized JIRA skills. It does not execute JIRA operations directly—it helps find the right skill.
Risk Levels
| Operation | Risk | Notes |
|---|---|---|
| Route to skill | - |
Read-only routing decision |
| Skill discovery | - |
Lists available skills |
| Context tracking | - |
In-memory only |
Risk Legend: - Safe, read-only | ! Caution, modifiable | !! Warning, destructive but recoverable | !!! Danger, irreversible
Quick Reference
| I want to... | Use this skill | Risk |
|---|---|---|
| Create/edit/delete a single issue, view/show issue details | jira-issue | ⚠️ |
| Search with JQL, export results | jira-search | - |
| Change status, assign, resolve, manage versions/components | jira-lifecycle | ⚠️ |
| Manage sprints, epics, subtasks, story points | jira-agile | - |
| Add comments, attachments, watchers | jira-collaborate | - |
| Link issues, view dependencies, blocker chains | jira-relationships | - |
| Log time, manage worklogs, time reports | jira-time | - |
| Handle service desk requests, SLAs, queues, approvals, assets, knowledge base | jira-jsm | - |
| Bulk operations on many issues (50+) with dry-run preview | jira-bulk | ⚠️⚠️ |
| Git branch names, commits, PR descriptions | jira-dev | - |
| Custom field discovery and Agile field configuration | jira-fields | - |
| Project discovery, cache management, diagnostics | jira-ops | - |
| Project settings, permissions, automation rules | jira-admin | ⚠️⚠️ |
Risk Legend: - Read-only/safe | ⚠️ Has destructive ops (confirm) | ⚠️⚠️ High-risk (confirm + dry-run)
Routing Rules
- Explicit skill mention wins - If user says "use jira-agile", use it
- Entity signals - Issue key present → likely jira-issue or jira-lifecycle
- Quantity determines bulk - 50+ issues → jira-bulk (consider bulk for 10+, required for 50+)
- Keywords drive routing:
- "show", "view", "display", "get", "retrieve", "see", "details", "look up", "check" (with issue reference) → jira-issue
- "create", "update", "delete" (single issue) → jira-issue
- "search", "find", "JQL", "filter" → jira-search
- "sprint", "epic", "backlog", "story points", "subtask" → jira-agile
- "transition", "move to", "assign", "close", "version", "release", "component", "resolve", "reopen", "archive" → jira-lifecycle
- "comment", "attach", "watch", "notify", "notification", "activity", "history", "changelog" → jira-collaborate
- "link", "blocks", "depends on", "clone", "dependency graph", "blocker chain" → jira-relationships
- "log time", "worklog", "estimate", "time report", "timesheet" → jira-time
- "service desk", "SLA", "customer", "request", "queue", "approval", "knowledge base", "asset" → jira-jsm
- "branch name", "commit", "PR" → jira-dev
- "custom field", "field ID" → jira-fields
- "cache", "warm cache", "project discovery", "diagnostics", "performance", "request batching" → jira-ops
- "permissions", "project settings", "automation", "automation rule", "users", "groups", "notifications", "screens", "issue types", "workflows", "notification scheme", "permission scheme" → jira-admin
What ships with it
60 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.
- docs/BEST_PRACTICES.md 16 KB
- docs/QUICK_REFERENCE.md 3.2 KB
- docs/ROUTING_REFERENCE.md 6.4 KB
- docs/SAFEGUARDS.md 6.0 KB
- docs/SCRIPT_EXECUTION.md 2.7 KB
- tests/build-enhanced.sh 6.8 KB runs code
- tests/claude_analyzer.py 12 KB runs code
- tests/claude-devcontainer/.github/workflows/docker-build.yml 3.5 KB
- tests/claude-devcontainer/.gitignore 290 B
- tests/claude-devcontainer/config/setup-enhanced.sh 10 KB runs code
- tests/claude-devcontainer/config/starship.toml 3.1 KB
- tests/claude-devcontainer/config/tmux.conf 3.9 KB
- tests/claude-devcontainer/Dockerfile 8.5 KB
- tests/claude-devcontainer/Dockerfile.enhanced 13 KB
- tests/claude-devcontainer/examples/Dockerfile.team 2.3 KB
- tests/claude-devcontainer/examples/team-config-private-registry.yaml 1.9 KB
- tests/claude-devcontainer/examples/team-config.yaml 1.5 KB
- tests/claude-devcontainer/lib/container.sh 9.2 KB runs code
- tests/claude-devcontainer/LICENSE 1.0 KB
- tests/claude-devcontainer/NO_EXTRA_CERTS 156 B
- tests/claude-devcontainer/README.md 9.1 KB
- tests/claude-devcontainer/scripts/build-enhanced.sh 6.8 KB runs code
- tests/claude-devcontainer/scripts/build-team-image.sh 14 KB runs code
- tests/claude-devcontainer/scripts/publish-to-registry.sh 12 KB runs code
- tests/claude-devcontainer/scripts/run.sh 20 KB runs code
- tests/claude-devcontainer/VERSION 6 B
- tests/conftest.py 13 KB runs code
- tests/dashboards/executive-summary.json 17 KB
- tests/dashboards/qa-test-engineer.json 23 KB
- tests/dashboards/skills-engineer-ab.json 18 KB
- tests/dashboards/sre-operations.json 17 KB
- tests/Dockerfile 2.7 KB
- tests/Dockerfile.dev 8.6 KB
- tests/Dockerfile.dev-enhanced 13 KB
- tests/docs/DASHBOARD_GAP_ANALYSIS.md 16 KB
- tests/docs/DASHBOARD_IMPLEMENTATION_PLAN.md 18 KB
- tests/enhanced/setup-enhanced.sh 10 KB runs code
- tests/enhanced/starship.toml 3.1 KB
- tests/enhanced/tmux.conf 3.9 KB
- tests/FAST_ITERATION.md 14 KB
- tests/fast_test.sh 6.4 KB runs code
- tests/grafana-dashboard.json 20 KB
- tests/lib_container.sh 8.2 KB runs code
- tests/NO_EXTRA_CERTS 357 B
- tests/otel_metrics.py 36 KB runs code
- tests/remediate_tests.py 26 KB runs code
- tests/requirements-otel.txt 240 B
- tests/requirements-test.txt 307 B
- tests/ROUTING_ACCURACY_PROPOSAL.md 14 KB
- tests/routing_golden.yaml 23 KB
- tests/run_container_tests.sh 6.1 KB runs code
- tests/run_devcontainer.sh 20 KB runs code
- tests/run_jira_devcontainer.sh 1.4 KB runs code
- tests/run_routing_tests.sh 2.8 KB runs code
- tests/run_sandboxed.sh 9.4 KB runs code
- tests/run_tests_loop.sh 2.5 KB runs code
- tests/run_workspace.sh 12 KB runs code
- tests/skill_editor.py 14 KB runs code
- tests/state_tracker.py 9.6 KB runs code
- tests/test_routing.py 31 KB runs code
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.
- 12d ago First seen · 236 lines · 37 tokens per session scan A 6cb85fda5795
jira-assistant is a skill published in the GitHub repository grandcamel/JIRA-Assistant-Skills (46 stars, last pushed 3d ago), licensed MIT. It adds 37 tokens to every session and 2,442 once invoked, about $0.0002 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
c-jira
Manage Jira issues using jira (jira-cli). List and filter issues, create new tickets, transition issue status, manage sprints, and add comments — all from the terminal without opening a browser.
reality-strategy
Change a blocked real-life or organisational situation by recovering the original result, reconstructing real participants and flows, investigating the sustaining cause, mapping stakeholders and practical power, then altering defaults, burdens, incentives, coalitions, information flow, decision rights or action…
mk:jira
Routing skill — recommends the correct mk:jira- leaf for any Jira task. Triggers: 'jira', 'jira ticket', ambiguous Jira intent. NOT an executor — every actual operation forks via a leaf skill.
Jira QA Workflows
Run QA work in Jira like a professional, bug lifecycle and triage, JQL queries for testers, quality dashboards, sprint QA rituals, and REST API automation for bulk bug operations and reporting.
ai-ml-development
AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.
python-logging-best-practices
Python logging with loguru, structlog, and orjson. TRIGGERS - loguru, structlog, structured logging.