Skip to content
Agentmart
Submit a tool

issue-tracker-comment

Shared jira/glab/bitbucket comment-posting commands for the optional "post this phase's output to the issue tracker" step every phase agent offers…

Skill by diego81b

IndexedAGPL-3.0★ 2
Write a review

Chalk Labs

Need help deploying issue-tracker-comment?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/diego81b-issue-tracker-comment

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Shared jira/glab/bitbucket comment-posting commands for the optional "post this phase's output to the issue tracker" step every phase agent offers, parameterized by output file and comment title.

Use cases: agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/issue-tracker-comment

What's inside

Skill name
issue-tracker-comment
Description
Shared jira/glab/bitbucket comment-posting commands for the optional "post this phase's output to the issue tracker" step every phase agent offers, parameterized by output file and comment title.
License
AGPL-3.0
Instructions
97 lines in SKILL.md · view on GitHub

Before installing

  • Instructions call the network

Agent Skills spec issues

  • name: missing

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Issue Tracker Comment

Shared reference for every phase agent's own "Issue Tracker Comment (optional)" step, invoked with two parameters the calling agent states inline: `{output_file}` (the `.kairos/<feature_folder>/` file to post) and `{title}` (the Markdown heading used as the comment's own title, e.g. `## Code Review`).

If the user provides an issue reference (Jira `PROJ-42`, GitLab/Bitbucket `#42`), post `{output_file}` as a comment on that issue once the human approves it at the phase's own HITL gate.

## Plain body

Most agents post the file with no extra heading — the tracker comment's own context (which pipeline run, which phase) is already clear from the issue thread.

**Jira** (`jira-cli`):
```bash
jira issue comment add PROJ-42 "$(cat .kairos/<feature_folder>/{output_file})"
```

**GitLab** (`glab`):
```bash
glab issue note <issue-id> --message "$(cat .kairos/<feature_folder>/{output_file})"
```

## Title-prefixed body

`pm-agent`, `architect-agent`'s implementer counterparts (`implementer-tdd-agent`, `implementer-coder-agent`), and `impact-assessment-agent` prefix `{title}` before the file content instead:

**Jira** (`jira-cli`):
```bash
jira issue comment add PROJ-42 "{title}\n\n$(cat .kairos/<feature_folder>/{output_file})"
```

**GitLab** (`glab`):
```bash
glab issue note <issue-id> --message "{title}\n\n$(cat .kairos/<feature_folder>/{output_file})"
```

## Extract body

`qa-plan-agent` posts a subset of its artifact rather than the file: its reader is a tester, and half of `05b-qa-plan.md` is pipeline bookkeeping that tester cannot act on. The agent's own step names which sections go in. In an orchestrated run the agent writes that body to `_qa-file.md` (the whole extract) and `_qa-comment.md` (the Core and a pointer line), and the orchestrator posts one of them after its gate, as the human chose (a plain body: `cat` that file, never `05b-qa-plan.md`). Standalone, the agent composes it inline — no `cat` of the artifact, and no second file written to hold the extract:

**GitLab** (`glab`):
```bash
glab issue note <issue-id> --message "$(cat <<'BODY'
{title}

<extract>
BODY
)"
```

**Jira** (`jira-cli`):
```bash
jira issue comment add PROJ-42 "$(cat <<'BODY'
{title}

<extract>
BODY
)"
```

A heredoc, not an inline string: the extract carries Markdown tables and backticks, and quoting those into a one-line argument is how a comment arrives mangled.

## Bitbucket (REST API)

Same shape for every agent regardless of plain/title-prefixed above:

```bash
curl -X POST "https://api.bitbucket.org/2.0/repositories/{workspace}/{repo}/issues/<id>/comments" \
  -u "${BITBUCKET_USER}:${BITBUCKET_TOKEN}" \
  -H "Content-Type: application/json" \
  -d "{\"content\":{\"raw\":\"{title}\"}}"
```

## No tracker CLI available

Never assume `jira`, `glab`, or `curl` is installed — corporate machines frequently have none of them, and an unguarded call fails in the middle of a phase gate. Before running any command above, check: `command -v jira`, `command -v glab`.

If none is present, or the command fails, **do not fail the phase** — the artifact is already durable on disk. Print the ready-to-paste comment body and the command the user can run later:

```
📋 Not posted automatically (<no tracker CLI found | post failed: <reason>>).
Paste this as a comment on <issue ref>:

<{title}, if this agent uses the title-prefixed form>

<content of .kairos/<feature_folder>/{output_file}>
```

Then continue. This applies to every agent below as well.

## No-Bash agents

`context-extractor-agent` and `documentation-agent` have no `Bash` tool (narrowed in v6.7.0 to match their stated contract). They cannot run the commands above themselves — extract `{output_file}`'s relevant section as the comment body and hand it, plus the matching command, to the user or orchestrator to run.

## Read-only agents

`security-reviewer-agent` and `impact-assessment-agent` have no `Write`/`Edit`/`Bash` at all (`tools: Read, Grep, Glob, AskUserQuestion`) — instruct the orchestrator to post on their behalf rather than running the command directly, same as their own Write-to-Project step.

From diego81b/kairos-agents-framework, AGPL-3.0.

More from diego81b/kairos-agents-framework

Signals

Stars
2
Forks
0
Open issues
0
Last commit (this folder)
Oct 7, 2026 (24 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
AGPL-3.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from diego81b

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get issue-tracker-comment running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying issue-tracker-comment?

CallGet help
Cite this page

issue-tracker-comment skill. Agent Mart. https://agentmart.dev/skills/diego81b-issue-tracker-comment (last updated 2026-10-24)