A mancode workflow for reproducing, diagnosing, fixing, and verifying a bug or regression, meaning a change that makes previously working behavior fail.

Handling bug reports, reproducing failures, identifying their cause, implementing a correction, and verifying the result.

It structures debugging so the reported failure is investigated and the fix is checked against the original problem.

manba — Skill for Claude Code and Codex by whitelonng: A mancode workflow for reproducing, diagnosing, fixing, and verifying…

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 skills/whitelonng/dshcode/manba

Any agent

npx skills add whitelonng/dshcode --skill manba

Clone the repo

git clone --depth 1 https://github.com/whitelonng/dshcode

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/whitelonng/dshcode/manba.svg)](https://agentmods.dev/skills/whitelonng/dshcode/manba)

Your own site

<a href="https://agentmods.dev/skills/whitelonng/dshcode/manba"><img src="https://agentmods.dev/badge/skills/whitelonng/dshcode/manba.svg" alt="Measured on agentmods" height="20"></a>

Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 754 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.

Model	Per session	Once invoked
Fable 5.1	$0.00013	$0.00754
Opus 5	$0.00006	$0.00377
Sonnet 5	$0.00003	$0.00151
Haiku 4.5	$0.00001	$0.00075

Measured 2d ago against content hash 6ba6a52d8fc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

manba 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 2d 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.

.agents/skills/manba/SKILL.md · 32 lines

How it starts

The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mancode mode: manba

Purpose: reproduce, diagnose, fix, and verify a regression.

Enter through mancode

Before the first command, use ./node_modules/.bin/mancode when it exists, otherwise mancode; check that selected binary with --version once and never mix binaries or versions. In every command below, replace the literal mancode with that selected binary path when the local binary exists.

Reuse a mancode status --brief --json snapshot already obtained in this conversation. Only when none exists, run it once from the project root. Never read or write the legacy authority file.
If identity.actorId is absent, ask for a display name and run mancode team identity create --name "<display name>".
Reuse session.sessionId when present. If status has no current session, reuse an explicit session ID already retained in this conversation. Only if neither exists, run mancode context session new --client codex in Codex, mancode context session new --client zcode in ZCode, or mancode context session new --client kimi-code in Kimi Code exactly once, then retain the returned session ID. Use --client codex in Codex, --client zcode in ZCode, or --client kimi-code in Kimi Code on every command that uses this session.
Reuse the current TaskRef. To bind a supplied existing task, run mancode context resume <namespace:ULID> --session <id> --client <active-client>.
For an existing task, read only the needed Context Pack with mancode context show --purpose implement --session <id> --client <active-client>; include --task <namespace:ULID> when it is not yet bound. For a new task, create it through the mode action first, then read the returned TaskRef's Context Pack.

Mode action

For a new diagnostic task, run mancode workflow create manba "<task>" --session <id> --client <active-client>.
Before changing code, establish the expected behavior from reproducible evidence, tests, documentation, history, or the current semantic owner. If the bug goal is clear but the correct behavior cannot be established, ask one focused question and wait instead of inventing product behavior.
If the requested fix conflicts with repository evidence or crosses a hard-risk boundary, show the conflict and obtain a focused confirmation or route the decision through /man; do not treat an explicit but unsound fix instruction as sufficient evidence.
When this is a child investigation, add --parent <namespace:ULID>; report and merge the typed outcome through the mancode child commands.
Change lifecycle only with mancode workflow update <namespace:ULID> --status <status> --expected-revision <n> --session <id> --client <active-client> and finish with workflow complete plus the typed --outcome.

Read the full file on GitHub · 32 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.

2d ago First seen · 32 lines · 13 tokens per session scan A 6ba6a52d8fc9

Subscribe to this mod's changes

manba is a skill published in the GitHub repository whitelonng/dshcode (712 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 754 once invoked, about $0.0001 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 2026-09-03.

Debugging agent deepseek deepseekharness-plugin dsh-plugin harness

visionary-cli

Analyze images with DeepSeek's vision model via the visionary-server CLI. Use this whenever the user provides an image, photo, screenshot, or document with images - run vision to look at it rather than guessing.

xlight/deepseek-visionary · 46 tokens

bug

Use when the user reports a bug or asks to capture one — ask the minimal questions needed, then produce a structured bug report the team can act on.

ccch1mneyyy/dsh-TUI · 33 tokens

deepseek-harness

Use when building AI agent applications with a plugin-based architecture — Web UI, CLI, Python SDK, Cordis plugin system, multi-model orchestration. DeepSeek Harness (dsh): open-source agent harness by DeepSeek AI where everything is a plugin, powered by Cordis for spatiotemporal composability.

znlgis/opengis-skills · 68 tokens

playwright-interactive

Persistent browser and Electron interaction through jsrepl for fast iterative UI debugging.

Haohao-end/openagent · 22 tokens

fixing

Diagnose why a PR's CI failed — compare the CI definition against the sandbox, classify the failure, and make the minimal repair. Use when a PR is red and you must work out why before changing anything.

nearform/lastlight · 46 tokens

lastlight-debug

Debug a running Last Light instance over its admin API with the lastlight CLI — no SSH. Use when the user wants to "look at / debug a failed or stuck workflow", "why didn't the bot do X", "check a bad agent run / phase error on ", "tail a session", "search the logs", "read the server/docker logs", "list/trigger a…

nearform/lastlight · 138 tokens