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 dcassil/resume-kit --skill update-shapegit clone --depth 1 https://github.com/dcassil/resume-kitWrote 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/dcassil/resume-kit/update-shape)<a href="https://agentmods.dev/skills/dcassil/resume-kit/update-shape"><img src="https://agentmods.dev/badge/skills/dcassil/resume-kit/update-shape/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/dcassil/resume-kit/update-shape"><img src="https://agentmods.dev/badge/skills/dcassil/resume-kit/update-shape.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 | $0.00081 | $0.01210 |
| Opus 5.5 | $0.00032 | $0.00484 |
| Sonnet 5.5 | $0.00016 | $0.00242 |
| Haiku 4.5 | $0.00008 | $0.00121 |
Grade A, and why
update-shape 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
update-shape — base → structure (canonical shape pass)
Baselining step 2 of the original → base → structure → refine pipeline
(RIT-I-0019). This skill gets the resume into the canonical resume shape after
the ATS structural base pass and before wording improvements. It drives the
deterministic analyze-shape and build-structure capabilities.
This is a structure-only pass. It is deterministic and non-destructive: it moves already-present content into canonical sections when the engine can account for every token, and it records lineage only after the content-ledger and cross-section claim gates pass. It does not rewrite wording, does not trim for budget, and does not remove content to make the resume shorter. Ambiguous mappings are deferred for the user; never guess.
The no-custom projection happens by default in build-structure. Parse must
always produce a faithful -original.json that retains customSections and
their headings; this step auto-seeds full-resume evidence, omits custom sections
from canonical output, and accounts for omitted custom content through the
content ledger and claim gates. The old --omit-custom-sections option is a
no-op compatibility alias.
Prerequisites
Run the shared Prerequisites gate —
../_shared/prerequisites.md.
- Required input: a
baseresume JSON — thebase_resumepointer inresume-kit/config.json. - Fallback input: if
baseis absent but anoriginalactive_resumeis present, the capability can analyze/build from the original; in the normal workflow, STOP and run update-structure first sobaseexists. - Does NOT need a job. Shape canonicalization is job-independent.
- If the resume JSON is missing (no
base_resumeoractive_resume, or a raw PDF/DOCX): STOP and run parse-resume, then update-structure.
What it does
- Shape analysis. Run the deterministic resume-only shape analyzer and show
the
ShapeReport(summary+findings). Use the activebaseJSON unless the caller explicitly supplies a different resume. - Auto-safe canonicalization. Run
build-structure: it idempotently seeds full-resume evidence, applies only the report-driven transforms the engine can account for, omits custom sections from canonical output, writesresume-kit/resumes/<name>-structure.jsononly when gates pass, and records thestructurepointer plusstructure_derived_fromlineage. - Surface deferred mappings. If findings are deferred or the build returns
structure_path: null, show the exact source sections and proposed targets from the report. Ask the user for explicit mappings before retrying. Do not infer a target from nearby content, job keywords, or personal preference. - Report applied vs deferred. Show
applied,deferred,ledger_ok,claims_ok, andstructure_path. If either gate fails, stop and report the failure; do not patch the JSON by hand.
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 First seen · 112 lines · 81 tokens per session scan A d854e31e6c97
update-shape is a skill published in the GitHub repository dcassil/resume-kit (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 81 tokens to every session and 1,210 once invoked, about $0.0003 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…