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/jsegov/shipspec-claude-code-plugin/implement-taskgit 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 | $0.00013 | $0.03438 |
| Opus 5 | $0.00006 | $0.01719 |
| Sonnet 5 | $0.00003 | $0.00688 |
| Haiku 4.5 | $0.00001 | $0.00344 |
Grade A, and why
implement-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 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.
How it starts
The opening of the file, as written. The whole thing — 383 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Task: $ARGUMENTS
Implement a specific task by ID, or find and implement the next available task.
Step 0: Parse and Validate Arguments
Parse $ARGUMENTS to extract:
- feature-dir (required): The first word/argument
- task-id (optional): The second word/argument, if provided
Normalize task-id format:
- If task-id is just a number (e.g.,
3), convert toTASK-003format (zero-padded to 3 digits) - If task-id is already in
TASK-XXXformat, use as-is - Store the normalized task-id for later use
If feature-dir is empty or missing:
"Error: Feature directory is required.
Usage:
/implement-task <feature-dir> [task-id]Examples:
/implement-task my-feature- implement next available task/implement-task my-feature 3- implement TASK-003 specifically/implement-task my-feature TASK-003- same as aboveTo see available features:
ls .shipspec/planning/ ```"
Stop here - do not proceed without a feature directory.
Step 1: Locate Feature Directory
Check that the feature directory exists:
ls -d .shipspec/planning/[feature-dir] 2>/dev/null || echo "NOT_FOUND"
If NOT_FOUND:
"No directory found for '[feature-dir]' at
.shipspec/planning/[feature-dir].Please run
/feature-planningfirst to create the planning artifacts."
Check for TASKS.json:
ls -la .shipspec/planning/[feature-dir]/TASKS.json 2>/dev/null || echo "TASKS.json NOT FOUND"
If TASKS.json not found:
"No TASKS.json found in
.shipspec/planning/[feature-dir]/.Run
/feature-planningto complete the planning workflow and generate tasks."
Step 2: Load, Parse, and Validate Tasks
Delegate to the task-manager agent with:
- Feature name: [feature-dir]
- Operation:
parse
If error (TASKS.json not found or empty): Show the error message from task-manager and stop.
If successful: Use the task map and statistics from the response.
Next, validate the task structure by delegating to task-manager with:
- Feature name: [feature-dir]
- Operation:
validate
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.
- yesterday First seen · 383 lines · 13 tokens per session scan A 8855ad5a7110
implement-task is a command published in the GitHub repository jsegov/shipspec-claude-code-plugin (20 stars, last pushed 7mo ago), licensed MIT. It adds 13 tokens to every session and 3,438 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.
Other commands, from other repositories
kiro-steering-custom
Command "kiro-steering-custom" from gotalab/cc-sdd, covering kiro custom steering creation, workflow, available templates, steering principles and tool guidance.
bench-capture
Score the 2 bench variant folders for one size (build/acceptance/regression/conventions/capture + rubric + cross-solution review), record, report, and reset.
autospec.plan
Generate YAML implementation plan from feature specification.
kiro-validate-design
Command "kiro-validate-design" from gotalab/cc-sdd, covering technical design validation, core task, execution steps, important constraints and tool guidance.
deploy
Build, test, deploy with staged rollout.
superpowers-execute
Execute the current GSD phase plan with Superpowers instead of gsd-execute-phase.