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 fayis672/slash-IT --skill create-cmd-instructgit clone --depth 1 https://github.com/fayis672/slash-ITWrote 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/fayis672/slash-it/create-cmd-instruct)<a href="https://agentmods.dev/skills/fayis672/slash-it/create-cmd-instruct"><img src="https://agentmods.dev/badge/skills/fayis672/slash-it/create-cmd-instruct/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/fayis672/slash-it/create-cmd-instruct"><img src="https://agentmods.dev/badge/skills/fayis672/slash-it/create-cmd-instruct.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 | $0.00017 | $0.00629 |
| Opus 5.5 | $0.00007 | $0.00252 |
| Sonnet 5.5 | $0.00003 | $0.00126 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
create-cmd-instruct 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.
What it actually says
The user wants to take their previous message — the most recent user turn in this conversation before this invocation — modify it according to extra instructions they provide here, and save the result as a reusable custom slash command.
Raw arguments: $ARGUMENTS
The arguments contain a command name and instructions for how to change the prompt,
separated by a | pipe. An optional scope flag may appear in the name part. Example:
/slash-it:create-cmd-instruct daily-report --project | output a markdown table and ask for the date
Do this:
- Split
$ARGUMENTSon the first|.- Left side = the command name (and optional scope flag).
- Right side = the user's instructions for reshaping the prompt.
If there is no
|, treat the first token as the name and the rest as instructions.
- From the left side, extract the name and any scope flag:
--global/-g/global-> system-wide.--project/-p/project-> this project.
- If the name is empty, STOP and ask for it (required). If the instructions are empty, ask what changes the user wants.
- Determine where to save (scope):
- If a scope flag was given, use it.
- Otherwise ASK with AskUserQuestion: "Where should
/<name>be saved?" -> Global or Project. - Global path:
~/.claude/commands/ - Project path:
<current working directory>/.claude/commands/— create if missing; fall back to Global if not in a project and say so.
- Normalize the name: lowercase, kebab-case, strip any leading
/and.md. - Find the user's previous prompt (the message right before this call).
- Produce a new prompt = the previous prompt transformed according to the instructions, plus
light optimisation (clarity, structure, grammar) while honoring the original intent. Parameterize
with
$ARGUMENTS/$1/$2where it makes the command reusable. - Briefly show the user the resulting prompt so they can see what was saved.
- Add YAML frontmatter with a one-line
descriptionand anargument-hintif parameters exist. - Write the file to
<chosen path>/<name>.md. - If that file already exists, show its current contents and ask before overwriting.
- Confirm: print the saved file path, the scope, and that
/<name>is now available.
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 · 44 lines · 17 tokens per session scan A 52840d68ad83
create-cmd-instruct is a skill published in the GitHub repository fayis672/slash-IT (2 stars, last pushed 3mo ago), licensed MIT. It adds 17 tokens to every session and 629 once invoked, about $0.0001 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
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies.
whats-next
Suggest what to work on next based on recent activity and current context. Use when the user is between tasks, at a decision point, wants direction on where to focus, or asks what to do next.
coaching-mode
Use when the user wants to coach someone — a report, peer, or mentee — through a problem rather than solve it for them. Trigger phrases include "coach me through how to talk to [report]", "I want to help [name] figure out X without telling them what to do", "let me practice a coaching conversation", "GROW conversation…
manage-glue-workers
Use when managing engineers who naturally gravitate toward glue work (onboarding, documentation, unblocking, process improvement) and need protection from burnout, visibility for their impact, and career development that doesn't force them off the IC track. Trigger phrases include "my report does too much glue", "how…
user-profile
Use to create or update the user's anchor profile — a single private file (/bettersense-work-reflections/profile.md) that captures who the user is, what they do, what context other skills need to know about them. Read automatically by other skills in the bundle when present, so the user doesn't re-explain themselves…
wins-log
Use when the user wants to capture a "win at work" — something they shipped, judgment they exercised, someone they mentored, a fire they put out, a hard decision they got right. Trigger phrases include "I just shipped X", "log this win", "add to my brag doc", "I want to remember what I did this week", "I had a good…