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 DanielC000/loom --skill codescapegit clone --depth 1 https://github.com/DanielC000/loomWrote 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/danielc000/loom/codescape)<a href="https://agentmods.dev/skills/danielc000/loom/codescape"><img src="https://agentmods.dev/badge/skills/danielc000/loom/codescape/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/danielc000/loom/codescape"><img src="https://agentmods.dev/badge/skills/danielc000/loom/codescape.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 | $0.00090 | $0.00942 |
| Opus 5.5 | $0.00036 | $0.00377 |
| Sonnet 5.5 | $0.00018 | $0.00188 |
| Haiku 4.5 | $0.00009 | $0.00094 |
Grade A, and why
codescape 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 1mo 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
codescape
Codescape is a code-graph MCP — a per-project, ingested snapshot of the repo's structure. When your
project exposes the Codescape MCP tools (overview / list_flows / describe_symbol / what_touches /
trace_flow / boundary_map / render_tree / scenario_space), it is your PRIMARY orientation
instrument, not a fallback.
The one thing to internalize: use the graph for structure, coordinates, and reachability, then open files ONLY to read the exact bytes you must verify or edit — at the coordinates the graph gave you. The graph REPLACES orient + locate; reading is only confirm/edit. If you re-derive the map by reading, or grep to LOCATE what the graph already pinpoints, you throw the whole point away — a measured speed / fewer-reads win collapses back into verify-by-reading.
Use the graph for three things
- ORIENT — the shape. What exists and how flows run through the system end to end (frontend + backend,
across parts/services). Reach a correct mental map with FAR fewer reads than opening files. Start here
(
overview/list_flows/trace_flow) before you open anything. - LOCATE — the coordinates. Which
file:lineeach piece lives at.describe_symbol/overview/what_touches/trace_flowreturn citation-gradefile:line— take the exact coordinates FROM the graph; don't grep to find what it already pinpoints. - REACHABILITY — what could happen. "What could render" (components + conditional branches) via
render_tree, and "what scenarios are possible" for one component — its loading/error/ready state space across data and mutation states — viascenario_space, which replaces hand-tracing every conditional yourself. Grep is actively BAD at these; the graph answers questions reading-by-hand can't.
Then read — targeted, at the coordinates
Open Read/grep ONLY for the irreducible step: the actual bytes you must verify or edit, opened DIRECTLY at
the file:line Codescape gave you — never searched for from scratch. A few pinpoint reads, not a re-explore.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +6 lines d2b423a95a65
- 1mo ago Changed · +3 lines 0e1b85fcfcd7
- 1mo ago First seen · 55 lines · 90 tokens per session scan A d3803a106399
codescape is a skill published in the GitHub repository DanielC000/loom (7 stars, last pushed yesterday), licensed MIT. It adds 90 tokens to every session and 942 once invoked, about $0.0004 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
build-test
Run the project's build / typecheck / lint / test commands and emit the build.passing + tests.passing signals devloop convergence reads.
patch-edit
Apply one rewrite-plan step at a time as small reviewable file edits, never rewriting whole files when a localised change suffices.
cvm-ai-doctor
A health-diagnosis workflow for servers, computers, virtual machines, and containers on Linux, macOS, or Windows.
fix-finding
Use when the user explicitly asks to fix and verify a validated or plausible security finding. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.
github-issue-solve
Solve a GitHub issue by collecting context, implementing a fix, and opening or updating a pull request.
compare-files
Compare two files and show differences.