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/andyrids/icm-spec/specnpx skills add andyrids/icm-spec --skill specgit clone --depth 1 https://github.com/andyrids/icm-specWrote 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/andyrids/icm-spec/spec)<a href="https://agentmods.dev/skills/andyrids/icm-spec/spec"><img src="https://agentmods.dev/badge/skills/andyrids/icm-spec/spec.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 | $0.00021 | $0.00469 |
| Opus 5 | $0.00010 | $0.00234 |
| Sonnet 5 | $0.00004 | $0.00094 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
spec 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 4d 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
Working under specs/
specs/ declares what MUST be true - permanent desired state, changed only by review. The full
protocol is specs/README.md; the authoring bar and templates are
ICM/_config/reference-standard-spec.md. Read both before writing.
The rules that bite most often:
- Specs state behaviour observable from outside the implementation - invocation, outputs, failure modes, errors. Never function names, module paths or test cases; those rot on the first refactor.
- Every spec carries
## Out of scope: the adjacent capability a reader would assume is included, and where it went. Edge cases stay in the spec too, asIf <trigger>, thencriteria. - Behaviour is stated in EARS (
ICM/_config/reference-standard-validation.md). The prose about authoring a spec stays in modal form; the requirements inside one do not. - The level-of-detail test: could two implementers read it and disagree about whether the code conforms? If yes, it is too vague.
- A new spec on the default branch needs an owning plan unless the behaviour already exists -
named in that plan's
specs:if code changes to conform, itsauthors:if the plan only writes the spec. Invariant 1 inspecs/README.md. - Every spec opens with the
context-hierarchy/context-hierarchy-role/immutable/tagsfrontmatter block inspecs/README.md. Without it the spec is not routable by layer. - After amending a spec, run the ripple check:
grep -l '<spec path>' plans/*.md, then flag the plans chasing the old desired state. - Spec/code divergence is a bug, not debt. Fix the code or amend the spec - never work around a spec in code.
Spec authorship belongs to ICM stage 01 (/icm:specify). Editing a spec mid-implementation is a
re-entry decision, not a quiet patch.
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.
- 4d ago First seen · 37 lines · 21 tokens per session scan A 4eb2ef6c3f13
spec is a skill published in the GitHub repository andyrids/icm-spec (2 stars, last pushed 15d ago), licensed Apache-2.0. It adds 21 tokens to every session and 469 once invoked, about $0.0001 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
tldr
Generate a review-oriented TLDR of GitHub Spec Kit artifacts (spec.md and/or plan.md) as a self-contained HTML dashboard plus a Markdown version, to make reviewing those files in a pull request faster. Use this skill whenever the user wants to review, summarize, "TLDR", skim, or get an overview of a Spec Kit spec.md…
tldr-delete
Remove generated speckit-tldr output — the .tldr.html and .tldr.md files and the specs/ /tldr/ directories that hold them — so these local review artifacts are not committed into a pull request. Use this skill whenever the user wants to delete, remove, clean, clear, or "clean up" the TLDRs that the tldr skill…
gsd-audit-milestone
Audit milestone completion against original intent before archiving.
spec-kitty-charter-doctrine
Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…
conductor-implement
Executes the tasks defined in the specified track's plan. Use this to start or continue working on a feature, bug fix, or chore.
ideogram-ultra
Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows with the local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL text encoder, and structured JSON ("compositional deconstruction") prompts for strong text rendering and layout control.