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/inadarei/claude-code-interactive-mode/document-contextgit clone --depth 1 https://github.com/inadarei/claude-code-interactive-modeWhat 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 | $0.00000 | $0.00564 |
| Opus 5 | $0.00000 | $0.00282 |
| Sonnet 5 | $0.00000 | $0.00113 |
| Haiku 4.5 | $0.00000 | $0.00056 |
Grade A, and why
document-context 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.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Document Project Context
Document everything you know about this project so that another session of Claude Code can be productive as soon as they check out this repository from git. Decide to analyze and survey the entire project first, if you do not already have full understanding of the project and how it is implemented, including its architecture and purpose. Pay attention to README.md file since it often contains valuable information
- Create fine-grained context files scoped to the directories where they matter
- Create any additional slash commands needed for repeatable tasks
- Carefully analyze opportunities for creating well-thought skills to make sure further code modifications follow existing architectural approaches, coding style, and best practices
- Do not add anything to the main CLAUDE.md except for a short (single small paragraph) synopsis of what the project is trying to achieve.
- Do add to top-level CLAUDE.md short (single small paragraph) synopsis of what the project is trying to achieve
- Make sure to create relevant skills
CRITICAL: Present a plan of what you are going to change in this project to achieve this, before modifying anything.
Skills are REQUIRED, not optional
Skills differ from commands in one critical way: Claude auto-invokes them
based on conversation context, without the user typing anything. They live
in .claude/skills/<name>/ as directories containing a SKILL.md file.
For any non-trivial project you MUST create at least 2 skills. Failure to create skills is a documentation failure.
What makes a good skill (auto-invocation is the key test)
Ask: "Would a new Claude session benefit from this knowledge being loaded automatically, without having to remember to ask for it?" If yes → skill. If it only helps when explicitly requested → command instead.
Good candidates:
- Architectural patterns a new session would likely get wrong (e.g. "adding a new provider using our Strategy pattern")
- Multi-step workflows with domain-specific sequencing that linting can't catch (e.g. "adding a new database query + migration + test")
- Patterns where the shape of the solution matters as much as correctness (e.g. "how we wire async thread-pool work in this codebase")
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 · 49 lines · 0 tokens per session scan A e92bbb9a5c56
document-context is a command published in the GitHub repository inadarei/claude-code-interactive-mode (11 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 564 tokens. 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.