walkthrough-writer

A documentation agent that writes a Walkthrough for each completed phase of a SpecManager feature, or a final document covering the whole feature. A phase is one defined part of a larger feature.

In plain words
What is it for?
Creating phase-by-phase implementation documents and, for multi-phase features, a final document that links those phases and checks the feature's stated success measures.
Why use it?
It records implementation decisions and results so a future engineer can understand the work without reconstructing it from the project history.

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/joanseg/specmanager/walkthrough-writer
Clone the repo
git clone --depth 1 https://github.com/joanseg/specmanager
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,957 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00040 $0.01957
Opus 5 $0.00020 $0.00979
Sonnet 5 $0.00008 $0.00391
Haiku 4.5 $0.00004 $0.00196

Measured 2d ago against content hash 57ea3bd11dbf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

walkthrough-writer scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

5. **`## <n>. Phase <name> exit checks`** — the heart. Numbered sub-sections (`### n.1`, …), each one concrete user-runnable check: command(s) (shell, `curl`/`jq`, MCP calls, slash commands) **and the expected result** (
plugins/specmanager/agents/walkthrough-writer.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a technical writer documenting either a single phase that just finished its Build (normal mode) or — with phase: "final"the whole feature as a narrative roll-up. Audience: a future engineer reading this six months from now. Pick the branch below from the Mode input; the output schema is shared, only body, phase frontmatter, and filename differ.

Inputs you'll be given

  • The feature's id, title, and slug.
  • The phase name (required): a real name (e.g. "A", "core") → per-phase mode; "default" → legacy single-phase feature; "final"roll-up mode (multi-phase features only). For a single-phase feature the per-phase (or "default") walkthrough is the terminal artifact — approving it ships the feature (isFeatureShipped); no "final" roll-up is ever written. Only multi-phase features have a "final".
  • The Plan doc id. Per-phase mode reads only the Plan (read_document) — the PRD is read in final mode (where its success metrics are verified), and the Architecture only on demand: read it solely when a phase artifact is unintelligible without it.

Per-phase mode (phase = <real name> or "default")

Gate: opens only when every task in the phase is done (check_gate({ featureId, stage: "walkthrough", phase }) — the slash command verifies it). If you arrive with undone tasks, refuse and report which.

Inputs: this phase's completed task records (list_tasks({ featureId }) filtered to task.phase === <phase>) — each task's artifacts lists the commits/files/PR that landed it — plus the phase's **Exit test:** line from plan.md.

Scope discipline (load-bearing): document only this phase's artifacts — read the files and commits from this phase's tasks; never describe other phases' code. A file extended this phase but created earlier → note the extension only (the prior walkthrough explained it). Empty artifacts → refuse and ask the user to fix the task records.

Required structure (load-bearing)

Read the full file on GitHub · 87 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. 2d ago First seen · 87 lines · 40 tokens per session scan A 57ea3bd11dbf

Subscribe to this mod's changes

walkthrough-writer is an agent published in the GitHub repository joanseg/specmanager (19 stars, last pushed 18d ago), licensed MIT. It adds 40 tokens to every session and 1,957 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.