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 MereWhiplash/engram-cogitator --skill customisinggit clone --depth 1 https://github.com/MereWhiplash/engram-cogitatorWrote 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/merewhiplash/engram-cogitator/customising)<a href="https://agentmods.dev/skills/merewhiplash/engram-cogitator/customising"><img src="https://agentmods.dev/badge/skills/merewhiplash/engram-cogitator/customising/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/merewhiplash/engram-cogitator/customising"><img src="https://agentmods.dev/badge/skills/merewhiplash/engram-cogitator/customising.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 | $0.00052 | $0.00916 |
| Opus 5 | $0.00026 | $0.00458 |
| Sonnet 5 | $0.00010 | $0.00183 |
| Haiku 4.5 | $0.00005 | $0.00092 |
Grade A, and why
customising 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 9d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customising
Tailor the workflow to this project through a guided negotiation. You advocate for the core values, offer the lighter mechanism first, then yield — recording the user's reasoning. Deltas only; upstream files are never edited.
Announce: "I'm using the customising skill to tailor the workflow."
The Loop
Listen → Map → Branch on friction → Write deltas → Set gate → Persist decision
Step 0: Load Context
- Read
cogitation/values.md(relative to the plugin root) — the six core values, which skills serve each, and the pitch for each. - Search prior customization decisions:
ec_search:
query: workflow customization
area: cogitation/customization
type: decision
If EC is down, proceed — the config file is still the source of truth.
Step 1: Listen
The user describes intent in plain language ("TDD is too strict here", "we don't do finishing-branch", "make brainstorming advisory"). Restate what you heard as a concrete change: which skill(s), toggled or re-tuned how.
Step 2: Map
Map each affected skill to the core value(s) it serves, using values.md.
This determines the friction tier.
Step 3: Branch on Friction
HARD — continuity-of-memory only. The one line that never yields. Do not
offer to switch off decision-persistence (ec_search/ec_add discipline,
remember). Say so plainly: "That's the one thing I can't move — without
memory there is no cogitation, just vanilla skills." Offer to serve it
differently (different cadence, different areas), never off.
Soft — everything else (advocate-then-yield):
- Advocate: cite the value's pitch from
values.mdand name the concrete failure mode the change re-exposes. - Offer the lighter mechanism first:
rigidity: advisorybeforeenabled: false; narrowing a skill's scope before removing it. - Yield: if the user still wants the stronger change, make it — with an explicit recorded acknowledgment ("Understood: disabling finishing-branch; you accept that merge hygiene is now manual. Reason: <user's words>").
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.
- 9d ago First seen · 108 lines · 52 tokens per session scan A 69f061798cbb
customising is a skill published in the GitHub repository MereWhiplash/engram-cogitator (4 stars, last pushed 2mo ago), licensed MIT. It adds 52 tokens to every session and 916 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…