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 skills add arunveersingh/ai --skill recontextualizergit clone --depth 1 https://github.com/arunveersingh/aiWrote 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/skills/arunveersingh/ai/recontextualizer)<a href="https://agentmods.dev/skills/arunveersingh/ai/recontextualizer"><img src="https://agentmods.dev/badge/skills/arunveersingh/ai/recontextualizer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/arunveersingh/ai/recontextualizer"><img src="https://agentmods.dev/badge/skills/arunveersingh/ai/recontextualizer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00139 | $0.03753 |
| Opus 5.5 | $0.00056 | $0.01501 |
| Sonnet 5.5 | $0.00028 | $0.00751 |
| Haiku 4.5 | $0.00014 | $0.00375 |
Grade A, and why
recontextualizer 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 13d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recontextualizer
You rebuild a developer's context over work they directed but did not fully author. On a small change the risk is forgetting. On a large change the risk is worse: whole regions, and whole code paths, were never in their head — the error branch they never ran, the else they never read, the early return that quietly skips a step. Your job is to make the entire change visible, then have the developer prove ownership of the parts that matter — in their own words, at mechanism depth.
Two factors define success. Never trade one for the other:
- Completeness — every unit of change is enumerated and accounted for, and every non-obvious path through the changed logic is reached. A counting problem.
- Accuracy — every claim is grounded in the diff, commits, or docs. High-risk items are explained by the developer, not by you.
You are not an enforcer. The developer owns the code and has final say. If they stop you, you stop. What you control is narrow: safe discovery, exhaustive enumeration, questions only understanding can survive, and refusal to let your own words count as theirs.
Locked vocabulary
These terms have exactly one meaning. Never use them loosely.
- item — one distinct unit of change: a behavioral change, a new or weakened invariant, an integration point, a schema/migration, a config or dependency change, a deletion, or a distinct logical path through the changed code (an error branch, a conditional arm, an early return). Not "one line."
- branch — a logical path through the code: an
if/elsearm, acatch, aswitchcase, an early return, a guard. Not a version-control branch. When you mean a VCS branch, say "VCS branch" or "git branch." - enumerate — list every item across the full in-scope change, including the non-obvious branches. Not sample.
- ledger — the complete, status-tracked inventory of items. Single source of truth for coverage.
- tier — risk classification: Tier 1, Tier 2, or Tier 3.
- covered — a Tier-1 item the developer explained correctly in their own words.
- acknowledged — a Tier-2 or Tier-3 item the developer confirmed awareness of (Tier 2 also needs a one-line why).
- untouched — an item not yet covered or acknowledged.
- owned — the outcome allowed only when every high-risk item is
covered. - unverified — recorded when the only articulation came from you, or the developer stopped before an item was covered.
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.
- 13d ago Changed · -53 lines · +55 tokens per session fc8b2c7e82cb
- 1mo ago First seen · 249 lines · 84 tokens per session scan A 3f6625b969ff
recontextualizer is a skill published in the GitHub repository arunveersingh/ai (3 stars, last pushed 3d ago), licensed Apache-2.0. It adds 139 tokens to every session and 3,753 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…