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.
npx agentmods add commands/joanseg/specmanager/specmanager-walkthroughgit clone --depth 1 https://github.com/joanseg/specmanagerWhat 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 | $0.00036 | $0.00848 |
| Opus 5 | $0.00018 | $0.00424 |
| Sonnet 5 | $0.00007 | $0.00170 |
| Haiku 4.5 | $0.00004 | $0.00085 |
Grade A, and why
specmanager-walkthrough 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.
How it starts
The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate a Walkthrough for $ARGUMENTS.
$ARGUMENTS is <featureId or slug> <phaseName | "final">.
phaseNameis the exact name fromplan.md's## Phase <name> — <theme>headings (e.g.A,core). For legacy single-phase features that pre-date phased plans, usedefault.finalwrites the feature-level roll-up that links every phase walkthrough. Only opens when every phase has anapprovedwalkthrough.
Steps
- Parse the arguments. Split into
<feature>and<phaseName>. If<phaseName>is missing, ask the user which phase (offerlist_phases({ featureId })to enumerate). - Resolve the feature.
list_features→ match byid/slug. - Single-phase
finalshort-circuit (refuse early). If<phaseName> === "final"andlist_phases({ featureId })returns exactly one phase, refuse before touching the gate: "Single-phase feature: the per-phase walkthrough is terminal; there is nofinalroll-up. Run/specmanager-walkthrough <feature> <thatPhaseName>instead." Approving that single per-phase walkthrough ships the feature (isFeatureShipped).finalis valid only for multi-phase features. Don't burn a gate round-trip or a subagent Task. - Check the gate.
check_gate({ featureId, stage: "walkthrough", phase: "<phaseName>" }). If closed, reportreasonand stop.- For a phase name: gate fails until every task in that phase is
done. - For
final: gate fails until every phase has an approved walkthrough (lists missing phases). (Only reachable for multi-phase features — single-phasefinalwas already refused in step 3.)
- For a phase name: gate fails until every task in that phase is
- Confirm no draft already exists for this phase.
list_documents({ featureId, stage: "walkthrough" })and filter tofrontmatter.phase === "<phaseName>". Don't duplicate. - Invoke the subagent.
Task({ subagent_type: "walkthrough-writer", prompt: ... }). Include:- Feature id, title, slug.
- The phase name (REQUIRED — drives which mode the agent runs in: per-phase or final).
- The Plan doc id.
- Per-phase mode: the phase's exit-test line lifted from
plan.md; hint that task artifacts for that phase are available vialist_tasksfiltered byphase. - Final mode: the list of phase walkthrough doc ids (look up via
list_documents({ featureId, stage: "walkthrough" })) — pass them explicitly so the agent doesn't waste tokens searching.
- Sync CLAUDE.md. Call
sync_claude_md. - Report. Document id + file path (e.g.
walkthroughs/<slug>/phase-<phaseName>.md, orwalkthroughs/<slug>/feature.mdforfinal). Suggest a user review pass before approving.
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 · 35 lines · 36 tokens per session scan A 39e48056a1e5
specmanager-walkthrough is a command published in the GitHub repository joanseg/specmanager (19 stars, last pushed 19d ago), licensed MIT. It adds 36 tokens to every session and 848 once invoked, about $0.0002 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 2026-08-30.
Other commands, from other repositories
version
Display current guide and Claude Code versions.
go-review
Go code review for idiomatic patterns.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
devs-team
Parallel multi-lens critique of a solution design (the active spec if present, else the decision brief). Dispatches 5 engineering lenses, merges findings, reports a verdict. Report-only, never blocks.
docs-review
Phase 4 of documenting-projects: Quality gate with 8 measurable criteria and iteration. Triggers: '/docs-review', invoked by documenting-projects orchestrator.
test
Run all PandaFilter verification steps in order. Stop and report on first failure. This is the required pre-commit gate.