furl

furl is a skill for Claude Code from omar-y-abdi/furl-ctx. It costs 95 tokens per session (5,872 once invoked), scanned A, original, Apache-2.0.

A context-compression add-on for Claude Code and Codex that reduces the token cost of large tool outputs while keeping removed content retrievable. Tokens are the text units used by language models.

In plain words
What is it for?
Compressing, retrieving, inspecting, searching, listing, measuring, and removing stored tool-output content through Furl MCP tools; Codex uses explicit compression calls.
Why use it?
It helps keep long tool results from consuming too much conversation space, while allowing specific omitted content to be requested later.

Skill for Claude Code

Written for Claude Code: PostToolUse hook event. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

Good fit Compressing, retrieving, inspecting, searching, listing, measuring, and removing stored tool-output content through Furl MCP tools; Codex uses explicit compression calls.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/omar-y-abdi/furl-ctx/furl
Install

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.

Any agent
npx skills add omar-y-abdi/furl-ctx --skill furl
Clone the repo
git clone --depth 1 https://github.com/omar-y-abdi/furl-ctx

Made for: Claude Code.

Wrote 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.

agentmods badge for furl

README.md
[![agentmods](https://agentmods.dev/badge/skills/omar-y-abdi/furl-ctx/furl/github.svg)](https://agentmods.dev/skills/omar-y-abdi/furl-ctx/furl)
Your own site
<a href="https://agentmods.dev/skills/omar-y-abdi/furl-ctx/furl"><img src="https://agentmods.dev/badge/skills/omar-y-abdi/furl-ctx/furl/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.

agentmods 80×15 button for furl

Your own site · 80×15
<a href="https://agentmods.dev/skills/omar-y-abdi/furl-ctx/furl"><img src="https://agentmods.dev/badge/skills/omar-y-abdi/furl-ctx/furl.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,872 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00095 $0.05872
Opus 5 $0.00048 $0.02936
Sonnet 5 $0.00019 $0.01174
Haiku 4.5 $0.00010 $0.00587

Measured 9d ago against content hash 946818229045, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

furl 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 9d 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.

plugins/furl-codex/skills/furl/SKILL.md · 293 lines

How it starts

The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Furl — context compression for Claude Code and Codex

Furl reduces the tokens large tool outputs cost by compressing them, while keeping every dropped byte retrievable on demand. It ships these capabilities:

  1. An MCP server (furl) exposing six tools in Claude Code and Codex.
  2. A retrieval-aware skill in both hosts.
  3. Automatic hooks in Claude Code only. Codex uses explicit furl_compress calls; its separate package root intentionally excludes Claude's incompatible hooks.

Retrieval is pull-based, not push-based. The compressed text you read does not contain the dropped rows. To inspect a specific dropped item, call furl_retrieve for it by pattern, field, or line range. Retrieval is byte-exact for raw text. A JSON array narrowed by select/fields comes back re-serialized — semantically complete but pretty-printed, so not byte-identical to the source; when byte fidelity matters (hashing, diffing, signature checks) pass raw: true on a row-select and each matched row returns byte-identical to its source bytes, the rows rejoined with fresh array punctuation, so each row is exact while the whole blob is not one contiguous slice.

What actually decides byte-exactness is the offload route, not text-vs-JSON. Content the router crushes structurally (columnar and tabular arrays) is stored as canonical json.dumps, so a full furl_retrieve returns canonical bytes — byte-identical only when your input was already canonical. Content offloaded whole-blob (plain text, or JSON too irregular to crush) is stored verbatim and returns byte-exact. One consequence on the crush path: the hash keys the canonical form, so two byte-different inputs that canonicalize the same collapse to one stored entry — on the crush path the hash is a semantic identifier, on the whole-blob path a byte one.

Nothing is lost, but a one-off anomaly buried in otherwise-repetitive data will not appear in the compressed view unless you query for it. Trust a compressed summary for the shape of the data, not for surfacing an anomaly you were not already looking for.

Read the full file on GitHub · 293 lines

Changes

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.

  1. 9d ago First seen · 293 lines · 95 tokens per session scan A 946818229045

Subscribe to this mod's changes

furl is a skill published in the GitHub repository omar-y-abdi/furl-ctx (4 stars, last pushed 7d ago), licensed Apache-2.0. It adds 95 tokens to every session and 5,872 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

sitrep

Situational awareness — where am I, what was I doing, what's next. Context recovery after compression, confusion, or mid-session reorientation.

martineserios/thebrana · 32 tokens

alive:save

The human wants to checkpoint. Or: the stash has grown heavy — 5+ items, 30+ minutes, a natural pause in the work. The squirrel doesn't decide when to save. It surfaces the need and lets the human pull the trigger. Runs the full save protocol: confirms stash, writes log, updates state, generates projections…

alivecontext/alive · 78 tokens

alive:session-history

Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…

alivecontext/alive · 76 tokens

alive:load-context

The human mentions a walnut to work on, asks about a specific venture/experiment/project, or wants to check status — not just explicit 'load X'. Load the brief pack (3 files), resolve the people involved, check the active bundle — then surface one observation and ask what to work on. Context loads in tiers: walnut and…

alivecontext/alive · 81 tokens

alive:mine-for-context

Deep context extraction from source material. Creates reference bundles, builds extraction plans, tracks what's been extracted, and discovers new targets — people, subjects, patterns, connections. The archaeologist that turns raw sources into structured knowledge. Can be invoked by alive:session-history for targeted…

alivecontext/alive · 63 tokens

alive:session-context-rebuild

Merge multiple sessions into one working context and detect conflicts between parallel sessions. Dispatches subagent swarm to read files touched, extract log history, and resolve contradictory state. Use when resuming after days away or when parallel sessions may have written conflicting decisions. For browsing or…

alivecontext/alive · 72 tokens