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 uHappyLogic/cairn --skill modify-milestone-goalgit clone --depth 1 https://github.com/uHappyLogic/cairnWrote 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/uhappylogic/cairn/modify-milestone-goal)<a href="https://agentmods.dev/skills/uhappylogic/cairn/modify-milestone-goal"><img src="https://agentmods.dev/badge/skills/uhappylogic/cairn/modify-milestone-goal/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/uhappylogic/cairn/modify-milestone-goal"><img src="https://agentmods.dev/badge/skills/uhappylogic/cairn/modify-milestone-goal.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 | $0.00037 | $0.00923 |
| Opus 5 | $0.00018 | $0.00462 |
| Sonnet 5 | $0.00007 | $0.00185 |
| Haiku 4.5 | $0.00004 | $0.00092 |
Grade A, and why
modify-milestone-goal 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.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
modify-milestone-goal
Replaces the ## Goal of the current milestone's requirements.md with a revised goal statement, then surfaces what the change may have invalidated downstream — leaving those follow-up edits to the user. It is the only skill that edits the Goal of an already-defined milestone.
Usage
/modify-milestone-goal <new or revised goal text>
<new or revised goal text>: either a complete replacement goal statement, or a described change to fold into the existing one (e.g. "also cover a quick-reference section"). If it is a delta, integrate it against the current Goal rather than discarding what is still true.
Example:
/modify-milestone-goal Broaden the getting-started guide to walk a new user through their first week, not only their first session.
Workflow
0. Find the current milestone
Follow .agents/plugins/cairn/shared/get-current-milestone.md to resolve <MILESTONE_DIR>. Never use a hardcoded path.
1. Read the current Goal
Read <MILESTONE_DIR>/requirements.md and locate the ## Goal section. Show the user the current goal text so the change is reviewable against what it replaces.
2. Determine the revised Goal
From the argument, settle on the new Goal prose:
- If the argument is a full replacement, use it (lightly cleaned for clarity).
- If it is a delta ("also…", "drop…", "really about…"), integrate it with the existing Goal so the result is a single coherent statement, preserving the parts still true.
If the intended change is genuinely ambiguous, state the revised wording you propose and confirm it with the user before writing. The Goal is the root of the whole requirements tree — getting its wording right matters more than acting fast.
3. Analyse the impact (before editing)
Reason about what the new goal may have invalidated. Do not write this analysis into the document and do not edit those sections — this is to inform what you surface in step 5:
- Which
## Decisionsentries the new goal contradicts, moots, or leaves dangling. - Which open or
Deferredquestions it newly settles, newly opens, or makes irrelevant. - Which
## Out of Scopeentries the new goal now pulls back in (or pushes out). - If
TASKS_TODO.md/TASKS_DONE.mdalready hold tasks, which derived or completed tasks the new goal strands, contradicts, or leaves unaddressed.
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 Changed 31f598e4fd8c
- 5d ago Changed · -9 lines · -109 tokens per session 62321515c3c2
- 10d ago First seen · 84 lines · 146 tokens per session scan A 72283731a4c8
modify-milestone-goal is a skill published in the GitHub repository uHappyLogic/cairn (2 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 923 once invoked, about $0.0002 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
debt-ops-add
Register a deferred decision in the tech-debt registry. Trigger by judgment, not a marker scan, whenever a future reader would ask "why this way?": an unmade decision, stub, loosened type, bypassed check, swallowed error, a default picked "for now", or a TODO/FIXME/HACK/XXX marker. Trigger immediately whenever you…
plan-task
Structured task planning using Work files. Use for any new feature, bug fix, or project that needs a task breakdown before implementation.
dont-leave-me
A stop-before-finishing checklist for an agent that checks whether requested work, changed files, verification, and cleanup have actually been handled.
log
Capture front door. Logs 1..N observations as card files at docs/work/{ID}.md (BUG / DEBT / GAP), gateway-inline — no dispatch. Use when the user says "log this", "track that", "note this down", or types /super-bootstrap:log — and when Claude needs to file its own findings (out-of-scope findings from a review, audit…
triage
Read-only grounding phase for a card — every card''s pickup. /super-bootstrap:triage {ID} dispatches the triage subagent (inherit — the session owner's model) to ground the card cold — premise verify, aim validate, blast collect — and append a Verdict block — ## Verdict — auto-fix · {date} (Fix-shape / Probe-deps /…
drain
Parallel-worktree auto-drain of the board. One /super-bootstrap:drain turn = scan the pipeline sources (specs/plans/backlog, plus the scale module's test queue when present) → keep only admissible items → relation-analyze into a conflict-free wave → confirm with the user → spawn one isolated git worktree + headless…