analyze-task

A command that classifies the current goal and changed files into one development route, such as research, bug fixing, or a code change.

In plain words
What is it for?
Use it to write the resolved route into `status.md`. It can select research, bugfix, code-change, or architecture work, while enforcing minimum requirements for higher-risk changes.
Why use it?
It helps choose an appropriate workflow automatically instead of making the user select a route manually.

Command

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 commands/fockus/skill-memory-bank/analyze-task
Clone the repo
git clone --depth 1 https://github.com/fockus/skill-memory-bank
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,005 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 $0.00019 $0.01005
Opus 5 $0.00010 $0.00502
Sonnet 5 $0.00004 $0.00201
Haiku 4.5 $0.00002 $0.00101

Measured 2d ago against content hash a3d741ac14c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyze-task 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.

commands/analyze-task.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.

/mb analyze-task

Auto-route the current flow. This is the default Dynamic Flow entry point (REQ-DF-020): read the durable goal.md and the git diff --name-only scope, classify a single candidate route from the catalogue, then hand that candidate to scripts/mb-flow-route.sh, which applies the deterministic route-floor (REQ-DF-022) and writes the resolved route: into the <!-- mb-flow --> fence in status.md.

Auto-routing is the default. To bypass classification with a fixed route, use the explicit escape-hatch /mb flow <route> (see commands/flow.md). Both paths still apply the route-floor and the firewall — the override never wins below the floor (REQ-DF-025).

The route catalogue

Pick exactly ONE candidate (lowest route that genuinely fits the work):

  • research — investigation/spike; no production code change expected.
  • bugfix — reproduce → debug → patch a localized defect.
  • code-change — the dominant case: a feature/change inside existing seams (reuses the work.md loop, ADR-7). Default when unsure.
  • arch — touches contracts, domain rules, ports/interfaces, or cross-module structure. The route-floor can FORCE this regardless of your pick.
  • migration — schema/data/dependency migration with ordering risk.

What it does

  1. Resolve the active Memory Bank (scripts/_lib.sh::mb_resolve_path).

  2. Read .memory-bank/goal.md (end-state + ## Acceptance criteria) and the changed-file scope from git diff --name-only (plus --cached).

  3. Classify a candidate route from the catalogue above.

  4. Call the resolver — it applies the floor and writes the fence:

    SKILL_DIR="$(cd "$(dirname "$0")/.." && pwd)"   # memory-bank skill bundle root
    bash "$SKILL_DIR/scripts/mb-flow-route.sh" --candidate <your-pick>
    
  5. Report the resolved route from the JSON the resolver prints ({"candidate":...,"floor":...,"route":...,"floor_triggered":...,"reasons":[...]}). If floor_triggered is true, say so and name the reasons — the floor overrode your candidate on purpose.

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 · 19 tokens per session scan A a3d741ac14c2

Subscribe to this mod's changes

analyze-task is a command published in the GitHub repository fockus/skill-memory-bank (25 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 1,005 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 2026-08-30.