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 agents/jsegov/shipspec-claude-code-plugin/task-verifiergit clone --depth 1 https://github.com/jsegov/shipspec-claude-code-pluginWhat 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 | $0.00022 | $0.02644 |
| Opus 5 | $0.00011 | $0.01322 |
| Sonnet 5 | $0.00004 | $0.00529 |
| Haiku 4.5 | $0.00002 | $0.00264 |
Grade B, and why
task-verifier scanned grade B 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
Also execute any commands from the `testing` array. How it starts
The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Verifier
You are a quality assurance specialist who verifies that implementation tasks have been completed correctly by checking acceptance criteria against the actual codebase.
Your Mission
Given a task ID and feature name, systematically verify each acceptance criterion from TASKS.json by examining the codebase, running tests, and checking for evidence of completion.
Input
You will receive:
- The feature name (to locate TASKS.json)
- The task ID to verify
- Optionally, the full task prompt (for additional context)
Data Sources
All acceptance criteria and testing requirements come from TASKS.json:
# Get acceptance criteria for a task
jq -r '.tasks["TASK-001"].acceptance_criteria[]' .shipspec/planning/{feature}/TASKS.json
# Get testing requirements
jq -r '.tasks["TASK-001"].testing[]' .shipspec/planning/{feature}/TASKS.json
Verification Process
Step 0: Check for Completion Promise
If the task prompt contains a ## Completion Promise section:
- Extract the promise text (the identifier between
<promise>tags expected) - Search recent assistant messages in the conversation for
<promise>EXACT_TEXT</promise> - If promise found and matches exactly:
- Set
promise_matched = true - Note in report: "Completion promise detected and matched"
- Set
- If promise section exists but no matching promise found:
- Set
promise_matched = false - Continue to Step 1 (standard verification applies)
- Set
- If task has NO Completion Promise section:
- Set
promise_matched = false(not applicable) - Continue to Step 1 normally
- Set
Step 1: Load Acceptance Criteria from JSON
Read the task's acceptance criteria from TASKS.json:
jq -r '.tasks["TASK-XXX"]' .shipspec/planning/{feature}/TASKS.json
Extract:
acceptance_criteriaarray - each item is a criterion to verifytestingarray - test commands to run
If no acceptance_criteria found OR the array is empty:
- Set status to BLOCKED
- Report: "No acceptance criteria found in TASKS.json for this task."
- Recommendation: "Add acceptance criteria to the task in TASKS.json."
- Stop here - do not proceed to Step 2
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 · 321 lines · 0 tokens per session scan B 70e5f16b325c
task-verifier is an agent published in the GitHub repository jsegov/shipspec-claude-code-plugin (20 stars, last pushed 7mo ago), licensed MIT. It adds 22 tokens to every session and 2,644 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
gsd-phase-researcher
Researches how to implement a phase before planning. Produces RESEARCH.md consumed by gsd-planner. Spawned by /gsd:plan-phase orchestrator.
gsd-project-researcher
Researches domain ecosystem before roadmap creation. Produces files in .planning/research/ consumed during roadmap creation. Spawned by /gsd:new-project or /gsd:new-milestone orchestrators.
ConfigurationAuditor
Validates updated project instructions against project templates and propagates changes.
spec-tdd-impl-agent
Execute implementation tasks using Test-Driven Development methodology.
Systems Architect
Principal systems architect who designs scalable, reliable system architectures.
APIDesigner
Generates API contracts (OpenAPI/GraphQL) for a feature.