evaluate-work

A command that examines a software work item and reports its current health. It checks its saved state, required files, approval gates, budgets, risks, and whether the work has gone stale.

In plain words
What is it for?
Use it to inspect a work item's progress, verify that required planning and review files exist, check remaining iterations and cost, and identify escalation points or stale runs.
Why use it?
It helps reveal missing records, blocked approvals, exceeded limits, or work that has stopped progressing before you continue.

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/agentic-swe/agentic-swe/evaluate-work
Clone the repo
git clone --depth 1 https://github.com/agentic-swe/agentic-swe
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 331 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 $0.00013 $0.00331
Opus 5 $0.00006 $0.00166
Sonnet 5 $0.00003 $0.00066
Haiku 4.5 $0.00001 $0.00033

Measured yesterday against content hash 04282d55f19b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evaluate-work 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.

commands/evaluate-work.md · 34 lines

What it actually says

/evaluate-work

Inspect an existing work item and assess its health.

Prompt

You are evaluating .worklogs/$ARGUMENTS/.

Instructions:

  1. Read .worklogs/<id>/state.json.

  2. Verify required artifacts exist for the current state using the artifact table in CLAUDE.md.

  3. Check timeout_at for staleness.

  4. Report:

    • current state
    • last transition (from history)
    • missing artifacts
    • gate status
    • budget status (remaining iterations, cost used vs budget)
    • loop counters
    • risk score and top items
    • whether the run is on the lean track or rigorous track
    • whether the run is at an escalation point
    • whether the work item is stale (past timeout_at)
  5. If this check is requested as an active repair step, update the work item files directly.

  6. Optional health scoring: Compare self-review.md (if present) to ${CLAUDE_PLUGIN_ROOT}/templates/evaluation-rubric.md — report any dimension still at 1 after rework limits, and whether metrics-summary.md exists under the work directory (optional file for cross-run metrics; not required by the state machine).

  7. Optional playbook signal: If docs/agentic-swe/PLAYBOOK.md exists in the repo, mention the most recent entry’s “next time” line when summarizing risks for the same area of work.

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 · 34 lines · 13 tokens per session scan A 04282d55f19b

Subscribe to this mod's changes

evaluate-work is a command published in the GitHub repository agentic-swe/agentic-swe (5 stars, last pushed 3mo ago), licensed MIT. It adds 13 tokens to every session and 331 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 2026-08-31.