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/jamie-bitflight/claude_skills/temp-docgit clone --depth 1 https://github.com/Jamie-BitFlight/claude_skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/jamie-bitflight/claude_skills/temp-doc)<a href="https://agentmods.dev/commands/jamie-bitflight/claude_skills/temp-doc"><img src="https://agentmods.dev/badge/commands/jamie-bitflight/claude_skills/temp-doc.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00023 | $0.04016 |
| Opus 5 | $0.00012 | $0.02008 |
| Sonnet 5 | $0.00005 | $0.00803 |
| Haiku 4.5 | $0.00002 | $0.00402 |
Grade A, and why
temp-doc 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 6d 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 — 579 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Temporary Documentation Lifecycle Command
Purpose
Manage temporary documentation created during task execution - prevent git pollution from AI-generated checklists, reports, and investigation notes.
Script Location
.claude/utilities/find-temp-documentation.py - Standalone Python script with Typer CLI.
Primary User: Claude Code orchestrator (not human users) Secondary User: Sub-agents (to update document status)
Critical Rules
PROBLEM: AI agents create temporary docs (bug reports, checklists, investigation notes) that:
- Pollute git history
- Confuse future AI sessions (treats fixed bugs as active)
- Create maintenance burden
- Are never read by humans or AI after task completion
SOLUTION: Enforce strict lifecycle for ALL temporary documentation.
Your Task
Apply temporary documentation lifecycle policy to: $ARGUMENTS
If $ARGUMENTS is empty, audit current directory for temporary docs and recommend cleanup.
Script Usage
For Orchestrator (Claude Code Main Instance)
Context-Efficient Workflow:
# Step 1: Check summary (50-100 tokens)
.claude/utilities/find-temp-documentation.py scan --summary
# Step 2: Peek at frontmatter of specific doc (100-150 tokens)
.claude/utilities/find-temp-documentation.py show --index 0 --frontmatter
# Step 3: Read full content only if needed (use Read tool)
Read("path/from/frontmatter")
# Step 4: Before completing task, cleanup completed docs
.claude/utilities/find-temp-documentation.py cleanup --no-dry-run
Common Scenarios:
# User asks: "What bugs did you find?"
# → Find bug reports quickly
.claude/utilities/find-temp-documentation.py scan --summary
# See: bugs: 2
.claude/utilities/find-temp-documentation.py show --index 0 --frontmatter
# description: "Bug tracking for config.py. 3 bugs (1 critical)"
# Multiple parallel tasks - organize by task
.claude/utilities/find-temp-documentation.py scan --group-by task
# Check what needs cleanup
.claude/utilities/find-temp-documentation.py cleanup # dry-run by default
# Actually cleanup (moves to .wastepaper/)
.claude/utilities/find-temp-documentation.py cleanup --no-dry-run
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.
- 6d ago First seen · 579 lines · 23 tokens per session scan A 9bf282b203b6
temp-doc is a command published in the GitHub repository Jamie-BitFlight/claude_skills (65 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 4,016 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.