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 skills/samplexbro/agentsmesh/update-target-capabilitiesnpx skills add sampleXbro/agentsmesh --skill update-target-capabilitiesgit clone --depth 1 https://github.com/sampleXbro/agentsmeshWrote 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/samplexbro/agentsmesh/update-target-capabilities)<a href="https://agentmods.dev/skills/samplexbro/agentsmesh/update-target-capabilities"><img src="https://agentmods.dev/badge/skills/samplexbro/agentsmesh/update-target-capabilities.svg" alt="Measured on agentmods" 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 | $0.00191 | $0.03939 |
| Opus 5 | $0.00096 | $0.01969 |
| Sonnet 5 | $0.00038 | $0.00788 |
| Haiku 4.5 | $0.00019 | $0.00394 |
Grade A, and why
update-target-capabilities 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.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Update Target Capabilities
Use this skill when an existing target already lives in src/targets/<target>/ and the underlying tool has started supporting a canonical feature that agentsmesh declares as none (or under-declares as partial/embedded) — or declares as native but doesn't actually work (wrong path, wrong key, wrong shape, generate-only with no importer, or a file the tool never reads). The job is to raise or correct that capability — for the right scope(s), with the generate and import sides symmetric — and to prove it.
The meta-rule: verify the claim before you build it. Most invocations of this skill act on a claim — an audit row, a feature-request, a changelog rumor, or a comment in our own code. In real use, a large fraction of those claims are wrong: the surface is fabricated (no such file exists), already-correct (the claim is stale), wrong-scoped (claimed "both scopes" but the tool only reads it globally), or GUI-only (no writable file →
partial, notnative). Treat every claim as a hypothesis and confirm it against the tool's own primary docs/source before writing a line. Rejecting a bad finding is a successful outcome — ship a guess and you ship a broken capability the matrix now advertises as real.
This is the skill add-agent-target defers to under "changing capability levels for an existing target." Use add-agent-target only for a brand-new target id; use add-global-mode-target only for first-time global wiring of a target that predates global support.
Read ./references/capability-update-checklist.md before editing code. It holds the decision matrices, the format/path-change blast-radius list, and the full touchpoint/test/review list.
When To Use
- A tool shipped a new feature surface (a config file, a settings key, a hooks format) that agentsmesh does not yet generate or import.
- You are auditing all targets for gaps ("which features do tools now support that we declare
none?"), or working through an audit/feature-request someone else produced (verify each row — see the meta-rule). - A capability is declared
partial/embeddedbut the tool now has a dedicated file surface agentsmesh could own natively. - A capability is declared
nativebut is broken: wrong path/key/shape, a file the tool never reads, or generate-only with no importer. Fixing it so the tool actually loads it (or so it round-trips) is in scope and counts as a real capability gain even though the matrix level doesn't move.
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.
- 2d ago First seen · 124 lines · 191 tokens per session scan A 427d6c633708
update-target-capabilities is a skill published in the GitHub repository sampleXbro/agentsmesh (24 stars, last pushed yesterday), licensed MIT. It adds 191 tokens to every session and 3,939 once invoked, about $0.0010 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 2026-09-03.
Other skills, from other repositories
skillshare-implement-feature
Implement a feature from a spec file or description using TDD workflow. Use this skill whenever the user asks to: add a new CLI command, implement a feature from a spec, build new functionality, add a flag, create a new internal package, or write Go code for skillshare. This skill enforces test-first development…
skillshare-update-docs
Update website docs to match recent code changes, cross-validating every flag against source. Use this skill whenever the user asks to: update documentation, sync docs with code, document a new flag or command, fix stale docs, or update the README. This skill covers all website/docs/ categories (commands, reference…
best-practices
Transforms vague prompts into optimized Claude Code prompts. Adds verification, specific context, constraints, and proper phasing. Invoke with /best-practices.
code-documentation
Writing effective code documentation - API docs, README files, inline comments, and technical guides. Use for documenting codebases, APIs, or writing developer guides.
audit-library-health
Use when checking the overall health of a skills library. Run doctor, validate, check for stale skills, and verify generated docs are in sync.
share-a-library
Use when a managed library is ready to publish to GitHub and hand to teammates as an install command. Run the GitHub publishing steps, then return the exact shareable install command.