Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/AndreVianna/aid-methodologynpx agentmods add skills/andrevianna/aid-methodology/aid-unset-connectorWrote 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/andrevianna/aid-methodology/aid-unset-connector)<a href="https://agentmods.dev/skills/andrevianna/aid-methodology/aid-unset-connector"><img src="https://agentmods.dev/badge/skills/andrevianna/aid-methodology/aid-unset-connector/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/andrevianna/aid-methodology/aid-unset-connector"><img src="https://agentmods.dev/badge/skills/andrevianna/aid-methodology/aid-unset-connector.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 | $0.00105 | $0.02121 |
| Opus 5.5 | $0.00042 | $0.00848 |
| Sonnet 5.5 | $0.00021 | $0.00424 |
| Haiku 4.5 | $0.00011 | $0.00212 |
Grade A, and why
aid-unset-connector 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 26d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unset Connector
aid-unset-connector <tool> removes one connector from .aid/connectors/ without touching any
other catalogued connector and without requiring — or triggering — an /aid-discover cycle. It is
the incremental, single-tool counterpart to aid-set-connector's upsert
(.agents/skills/aid-set-connector/SKILL.md), and shares its reconcile.md single-stem plumbing.
Absent from the mandatory pipeline flow. Like aid-set-connector, /aid-config, and
/aid-housekeep, this is an optional, on-demand skill — no phase gate references it, and it never
invokes /aid-discover.
Keyed by <tool> → one descriptor, unconditionally removed. Unlike aid-set-connector's
ADD-vs-UPDATE classification, this skill has exactly one class: REMOVE. Whether <tool>'s stem is
currently catalogued or not, the same purge-then-delete sequence runs — on an already-absent stem
both operations are themselves clean no-ops (idempotent by construction; AC5), never a
special-cased branch that checks first and skips.
Pre-flight
DefaultorAuto-accept edits→ proceed.Plan mode→ STOP. This skill deletes files under.aid/connectors/.- Requires exactly one positional argument:
<tool>. No optional flags.
Step 0: Validate arguments
- Not exactly one positional argument → print and exit non-zero:
Usage: aid-unset-connector <tool> Example: aid-unset-connector Jira - Any flag or extra argument is unknown:
exit non-zero.Unknown argument: <arg> Usage: aid-unset-connector <tool>
From here on, $TOOL names the resolved <tool> argument (already validated above) — used as a
shell variable in the bash snippets below, never as literal angle-bracket text.
Step 1: Resolve <tool> → descriptor stem
Derive the stem exactly as ELICIT and aid-set-connector do (feature-002's slug rule) — lowercase,
non-alphanumeric runs collapsed to -, no leading/trailing -:
STEM=$(echo "$TOOL" | tr '[:upper:]' '[:lower:]' | sed -E 's/[^a-z0-9]+/-/g; s/^-+|-+$//g')
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.
- 26d ago Changed 41b16cccbd1b
- 2mo ago First seen · 170 lines · 105 tokens per session scan A 48edc3895be1
aid-unset-connector is a skill published in the GitHub repository AndreVianna/aid-methodology (6 stars, last pushed 11d ago), licensed MIT. It adds 105 tokens to every session and 2,121 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 2026-09-03.
aid-unset-connector compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| aid-unset-connectorAndreVianna/aid-methodology | Skill | 6 | 11d ago | MIT | A | 105 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |