_bug-report-protocol

A shared protocol for recording bugs, improvements, and unclear requirements found during development or testing.

In plain words
What is it for?
Deciding when to create follow-up tasks, checking for duplicate reports, and passing structured findings from developer and tester agents to a session manager.
Why use it?
It prevents issues outside the current task from being silently forgotten or lost between agents.

Agent

Install

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.

agentmods
npx agentmods add agents/alphaelements/handoff-mcp/_bug-report-protocol
Clone the repo
git clone --depth 1 https://github.com/alphaelements/handoff-mcp
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 717 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00717
Opus 5 $0.00000 $0.00358
Sonnet 5 $0.00000 $0.00143
Haiku 4.5 $0.00000 $0.00072

Measured yesterday against content hash 681e027a157d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

_bug-report-protocol 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.

plugin-task-loop/agents/_bug-report-protocol.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bug/Improvement Report Protocol (shared)

Shared rules for session-developer / session-tester / session manager to ensure bugs and improvements found during work are never silently swallowed but recorded as new handoff tasks.

This file is referenced by each agent definition.

When to create a report task

Whenever you find something outside the current task's scope:

  • Bug: Existing/new code defects, regressions, spec deviations, unhandled edge cases.
  • Improvement: Refactoring opportunities, performance, UX, test gaps, convention violations, tech debt.
  • Spec ambiguity/contradiction: Discrepancies between spec documents or between spec and code.

Decision criteria:

  • Trivial and in-scope -> fix it on the spot (don't create a separate task).
  • Out of scope or deserves independent tracking -> create a report task.
  • When in doubt, create it (don't swallow it). But check for duplicates first via handoff_list_tasks.

How sub-agents (developer / tester) report

Sub-agents don't call handoff directly. Instead, include structured findings in the return value. The manager creates the actual handoff tasks. Include this section in your report:

### Discovered issues (report task candidates)
- **[bug|improvement|spec] title**
  - Description: <what's wrong. Reproduction steps if applicable>
  - Location: <file:line range> (multiple OK)
  - Spec link: <wiki/xx.md#section or docs/plans/... if applicable>
  - Proposal: <current -> proposed -> benefit>
  - Severity: high|medium|low
  - Relationship to current task: <why this is a separate task, not an in-scope fix>

If nothing found, explicitly write: ### Discovered issues: None (don't stay silent).

How the session manager creates report tasks

When receiving "Discovered issues" from sub-agents, before closing the task, create new tasks via handoff_update_task (omit id for auto-assignment):

  • title: [bug] / [improvement] / [spec] prefix + concise title
  • status: todo (backlog only — don't start working on it)
  • priority: Match the sub-agent's severity (high/medium/low)
  • labels: ["found-during-loop", "<type>"] (for later filtering)
  • links: File paths (file:line) + spec document paths/URLs
  • notes: Description, reproduction steps, current -> proposed -> benefit proposal, relationship to the originating task. Include originating task ID and session ID for traceability.
  • done_criteria: At least one criterion defining "what makes this resolved".

Read the full file on GitHub · 69 lines

Changes

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.

  1. yesterday First seen · 69 lines · 0 tokens per session scan A 681e027a157d

Subscribe to this mod's changes

_bug-report-protocol is an agent published in the GitHub repository alphaelements/handoff-mcp (0 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 717 tokens. 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 2026-08-31.