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 tikalk/adlc-team-skills --skill change-clarifygit clone --depth 1 https://github.com/tikalk/adlc-team-skillsWrote 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/tikalk/adlc-team-skills/change-clarify)<a href="https://agentmods.dev/skills/tikalk/adlc-team-skills/change-clarify"><img src="https://agentmods.dev/badge/skills/tikalk/adlc-team-skills/change-clarify/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/tikalk/adlc-team-skills/change-clarify"><img src="https://agentmods.dev/badge/skills/tikalk/adlc-team-skills/change-clarify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00039 | $0.02922 |
| Opus 5.5 | $0.00016 | $0.01169 |
| Sonnet 5.5 | $0.00008 | $0.00584 |
| Haiku 4.5 | $0.00004 | $0.00292 |
Grade A, and why
change-clarify 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 25d 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 — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.
change-clarify
What this skill does
Review pending ChDRs (status Discovered or Proposed) and decide their fate: Accepted, Rejected, or Deferred.
This is the quality gate for Change Decision Records — the human checkpoint before inferred-from-history decisions are promoted to project memory and injected into future sessions by team-boot:
- Validate that inferred decisions are supported by cited commit SHAs / issue URLs (provenance — the context-poisoning circuit breaker)
- Check inferred-rationale confidence and flag low-confidence or unsupported claims
- Confirm issue-link validity and that fetched issue summaries are accurate (not pasted verbatim)
- Ensure Consequences (reverts/fix chains) are recorded where observed
- Update ChDR statuses in
{REPO_ROOT}/.adlc/drafts/chdr/ChDR-{NNN}.md - Regenerate
{REPO_ROOT}/.adlc/drafts/chdr/chdr.mdindex
This is an interactive command. Present exactly one ChDR per interaction and wait for user input.
When to use
- After
/change-init: validate history-mined ChDRs before promotion - Periodic review: clean up stale pending ChDRs
When NOT to use
- No pending ChDRs: if no ChDRs have status Discovered/Proposed, there is nothing to clarify
- Reviewing CDRs: use
/team-levelup(CDRs and ChDRs are distinct record types with separate gates) - Direct editing: do not use this skill to bypass the review workflow
Process
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
Examples of User Input:
"ChDR-001 ChDR-003"— focus on specific ChDRs"all"— clarify all pending ChDRs- Empty input: clarify all ChDRs with status "Discovered" or "Proposed"
Flags
--all: clarify all pending ChDRs (same as empty input)--limit N: limit to N clarifications per session (default: 5)
Role & Context
You are acting as a Change Validator reviewing inferred-from-history decisions. Unlike CDR clarification (which validates team-wide patterns), your focus is evidence fidelity:
What ships with it
2 files 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.
- 25d ago Changed edf938603980
- 1mo ago Changed · +20 lines 4b9ac01ee01f
- 1mo ago Changed · -11 tokens per session b8ab23cf9cb7
- 1mo ago First seen · 359 lines · 50 tokens per session scan A 2a766869dd2f
change-clarify is a skill published in the GitHub repository tikalk/adlc-team-skills (143 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 2,922 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
building-agents
Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…
agent-eval
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…
decision-records
Use when a hard-to-reverse choice (database, framework, vendor, auth model) must be frozen as an immutable numbered ADR — the context that forced it, the options weighed, the decision, consequences both ways — or superseded without erasing history. NOT a meeting recap (that is meeting-notes), NOT standing project…
prompt-engineering
Use when one prompt must give the same right answer across reruns, models, and pasted-in hostile input: forcing a fixed schema, picking the few-shot set, ordering the prompt blocks, or the inline cases you run while tuning. NOT the agent loop, tools, or retrieval (that is building-agents), NOT a standing CI eval…
respect-the-oracle
Use when working against a test suite, spec, or graded harness you do not own - especially inside an automated loop scored on how many tests pass - and tempted to change the tests, weaken assertions, hardcode expected outputs, special-case inputs, or overfit the visible examples to turn things green.
refocusing
Use when a long-running agent may have lost the product outcome, when context was compacted, when work has crossed a major boundary, or when a fresh path-based trace is needed before the next consequential action. Not for fresh-session orientation, waking an idle seat, or checkpoints.