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/fvckprth/remediate/sync-docsgit clone --depth 1 https://github.com/fvckprth/remediateWhat 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 | $0.00014 | $0.00443 |
| Opus 5 | $0.00007 | $0.00221 |
| Sonnet 5 | $0.00003 | $0.00089 |
| Haiku 4.5 | $0.00001 | $0.00044 |
Grade A, and why
sync-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
Sync Docs
keep the docs site, agent skill, and package README in sync after changes.
when to run
after any change to: recipes, props, payload shape, component API, capture types, or server helpers.
sources of truth
- docs site (
/Users/parthpatel/Desktop/Projects/remediate-mktg/src/app/docs/) — the canonical reference - agent skill (
skills/remediate/SKILL.md) — must match the docs recipes and component patterns - package README (
README.mdat repo root) — quick-start subset of the docs
steps
-
identify what changed
- if
$ARGUMENTSis provided, use it as the description of what changed - if empty, diff the docs site against the skill and README to find mismatches
- if
-
read current state of all three
- read the relevant docs pages (install, recipes, payload, reference)
- read
skills/remediate/SKILL.md - read
README.md
-
update the skill
- sync recipe templates to match docs (same code, same type narrowing, same file handling)
- sync backend detection signals if new backends were added
- sync component mounting instructions if props changed
- sync notes section if capture types or API changed
-
update the README
- sync the server route example to match the install page
- sync the props table to match the reference page
- sync capture type descriptions if they changed
- keep the README minimal — it's a quick-start, not the full docs
-
commit and push both repos
- skill + README changes in the package repo:
docs: sync skill and readme with docs site - if docs site needed fixes too, commit those separately in remediate-mktg
- skill + README changes in the package repo:
-
confirm
- list what was updated in each file
- flag anything that looked inconsistent but wasn't clear how to resolve
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 · 14 tokens per session scan A 2ea73886c5f9
sync-docs is a command published in the GitHub repository fvckprth/remediate (11 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 443 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.