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/riekelt/technical-writer/ground-docsgit clone --depth 1 https://github.com/riekelt/technical-writerWhat 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 | $0.00011 | $0.00365 |
| Opus 5 | $0.00005 | $0.00182 |
| Sonnet 5 | $0.00002 | $0.00073 |
| Haiku 4.5 | $0.00001 | $0.00036 |
Grade A, and why
ground-docs 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.
What it actually says
Launch a documentation campaign for the system at the given path (default: the current repository) per the documenting-legacy-codebases skill, which governs everything this command does not state.
Arguments: $ARGUMENTS
Sequence:
- Load the skill first:
documenting-legacy-codebases, withtechnical-writingas its required background. The skill's body is the authority; this command is only the entry point. - Survey before prose. Enumerate the system's surfaces per the skill's inventory list, with the command and date behind every count.
- Present the plan before writing: the derived docs tree, the coverage denominators, and the model tiers per campaign phase. Wait for the user's go on the plan.
- Run the campaign per the skill's fan-out:
doc-grounderagents ground per subsystem, each pipelined into aprose-reviewerfor the fresh-eyes pass. Pass each agent an explicit model per the skill's tier labels (small to mid-sized for grounding, mid-sized for review); the agents' own defaults do not enforce the ceiling. You are the campaign's only writer: write each returned document to its planned path in the docs tree, and keep the coverage ledger, findings note, and unknowns file current as results land. - Assemble last per the skill, and close by reporting the ledger: what is drafted, what is reviewed, what is unknown, and what landed in the findings note for the owner.
On interruption at any point, the ledger is the hand-off: leave it stating exactly what is done and what is outstanding.
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 · 19 lines · 11 tokens per session scan A d3559303df56
ground-docs is a command published in the GitHub repository riekelt/technical-writer (15 stars, last pushed 2d ago), licensed MIT. It adds 11 tokens to every session and 365 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.