
agora-reporting
Report coding-agent progress, questions, decisions, blockers, tests, PRs, human replies, inbox instructions, and handoffs to the Agora coordination server. Use for every coding task when AGORAURL is set, especially at session start, before risky or shared edits, when blocked, when asking for human or agent input, after running tests or verification, when opening or updating PRs, when polling for human replies or instructions, and before the final response.
- Installs
- 308
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/kelos-dev/agora --skill agora-reporting- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads agora-reporting automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Agora Reporting
Use Agora as the shared coordination feed for human and agent work. If
AGORA_URL is unset, skip Agora reporting without blocking the task.
The server-backed commands post, inbox, and status require AGORA_URL;
session does not contact the server and does not require AGORA_URL.
Setup
Resolve the helper once:
AGORA_REPORT="agora"
The agora CLI must be available on PATH.
Use these environment variables when present:
AGORA_URL Agora server base URL, such as http://127.0.0.1:8080
AGORA_AGENT agent handle to use as actor
AGORA_THREAD default thread name
AGORA_TOKEN optional bearer token
Create one thread per coding-agent session unless a launcher or human already selected a thread:
if [ -z "${AGORA_THREAD:-}" ]; then
eval "$($AGORA_REPORT session)"
fi
Keep that AGORA_THREAD value for the lifetime of the agent process so progress,
questions, verification, and handoff posts stay together.
Required Loop
When AGORA_URL is set:
- At session start, post a
summarywith the task you are starting. - Poll your inbox before major work and at natural breakpoints.
Treat targeted human replies, comments, decisions, questions, and instructions as user input for the current task.
Acknowledge actionable inbox items before acting on them, then mark them
done,resolved, orrejectedwhen handled. - Before risky or shared edits, post
code_changedorsummarynaming the planned scope. - When blocked, post
blockedwith the concrete blocker and next needed input. - When asking for input, post
questionwith--target humanor the target agent. - After verification, post
tests_passedortests_failedwith the command and result. - Before final response, post
handofforsummarywith outcome, verification, and residual risk.
Keep posts short and decision-worthy. Do not paste raw logs; summarize and link or name artifacts instead.
Commands
Post an event:
$AGORA_REPORT post --type summary --title "Started task" --body "Reading the repo and planning changes."
Create a session thread:
$AGORA_REPORT session
$AGORA_REPORT session --format value
Post a targeted question:
$AGORA_REPORT post --type question --target human \
--thread api-design \
--title "Choose compatibility behavior" \
--body "Option A preserves existing manifests. Option B is cleaner but breaking."
Poll your inbox:
$AGORA_REPORT inbox
Use --all only when you need closed or already handled items.
Mark an instruction or question:
$AGORA_REPORT status <event-id> acknowledged
$AGORA_REPORT status <event-id> done
Event Types
Prefer these event types:
summary, question, instruction, comment, decision, blocked, code_changed,
tests_passed, tests_failed, pr_opened, review_received, ci_failed, ci_passed,
ci_completed, handoff
FAQ
What does the agora-reporting skill do?
Report coding-agent progress, questions, decisions, blockers, tests, PRs, human replies, inbox instructions, and handoffs to the Agora coordination server. Use for every coding task when AGORAURL is set, especially at session start, before risky or shared edits, when blocked, when asking for human or agent input, after running tests or verification, when opening or updating PRs, when polling for human replies or instructions, and before the final response.
How do I install agora-reporting?
Run npx skills add https://github.com/kelos-dev/agora --skill agora-reporting in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/agora-reporting/ (personal) or .claude/skills/agora-reporting/ (project).
Which AI agents can use agora-reporting?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is agora-reporting safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains agora-reporting?
It is published by kelos-dev in kelos-dev/agora. It has 308 recorded installs.
Popular testing & qa skills
tdd
mattpocock/skills
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
grilling
mattpocock/skills
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
migrate-to-shoehorn
mattpocock/skills
Migrate test files from as type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace as in tests, or needs partial test data.
run-train
lllllllama/rigorpilot-skills
Rigor Train skill for deep learning research repositories. Use when a documented or selected training command should be run conservatively for startup verification, short-run verification, full kickoff, or resume, with command, config, seed, log, checkpoint, status, and metric evidence written to standardized trainoutputs/. Do not use for environment setup, exploratory sweeps, speculative idea implementation, or end-to-end orchestration.
test-driven-development
obra/superpowers
Use when implementing any feature or bugfix, before writing implementation code
finishing-a-development-branch
obra/superpowers
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work